Paper library

Papers, datasets, benchmarks, and reading notes on World-Action Models.

564 entries8 major categories1989 – 2026 recorded publication yearsUpdated 13 Sept 2026

Papers

About the classification

Programmable World Model

Zheng-Hui Huang; Guixu Lin; Jiacheng Lin +8 authors

Benchmarks & simulators Not applicable

9 Sept 2026

Programmable World Model makes a rule-executing engine authoritative for world facts and uses a conditioned video model to render them. State-augmented 3D oriented bounding boxes connect these components without requiring detailed animated assets. On CombatStateBench, the system reports 94% visible-alive-count accuracy and 98% death-state accuracy, but these permissive global metrics do not establish correct entity-specific interactions or autonomous action selection (e-world, e-controls, e-table, e-metrics).

IllustratedReading report

DUET-DINO: Simultaneous Cross-View World Modeling for Latent Planning in Robot Manipulation

Nisarga Nilavadi; Ralf Römer; Moritz Reuss +5 authors

WAMs Outside quadrants

9 Sept 2026

DUET-DINO couples side- and wrist-camera latent predictors through cross-attention, then searches seven-dimensional robot actions against paired goal images. Its clearest evidence is improved simulated spatial and orientation planning; hardware success remains limited under a smaller planning budget and safety terminations (e-architecture, e-planning, e-angled, e-hardware).

IllustratedReading report

FolDeX: A Physical-World Benchmark for Long-Horizon Robotic Manipulation of Deformable Objects

Chenhuan Liu; Yi Xu; Feng Wu +7 authors

Benchmarks & simulators Not applicable

9 Sept 2026

FolDeX evaluates complete physical garment-folding episodes and asks whether expensive robot experience can be reused across recovery states, tasks, scenes, and embodiments. Its reference policies use π0. Recovery-augmented training raises reported average success from 80.75% to 95.00%, but transfer studies remain preliminary and the missing quality-scoring appendix prevents independent reconstruction of FoldScore from the supplied paper alone.

IllustratedReading report

Grounding Generated Video Plans in Simulation Towards Versatile Dexterous Controllers

Tianyue Wu; Boyuan An; Shuqi Zhao +6 authors

WAMs Outside quadrants

9 Sept 2026

GALATEA turns image-and-language-conditioned manipulation videos into 3-D hand–object references, then learns simulation-based controllers that physically track them. Its central interface retains finger motion and object motion together. Multi-skill experts are distilled into one feedback policy; simulated transfer and 27/40 real-world successes on unseen plans support useful, but limited, generalization (e02, e09, e14, e17).

IllustratedReading report

HaWMPO: Hallucination-Aware World Model-based Policy Optimization for Generalist Robot Policy

Zengjue Chen; Peidong Liu; Jiawei Li +1 authors

WAMs Outside quadrants

9 Sept 2026

HaWMPO post-trains OpenVLA-OFT inside a frozen video world model. A separate hallucination detector discounts rewards assigned to unreliable imagined action chunks before GRPO updates the policy. Table 1 reports 63.7% average LIBERO success, but gains vary by suite and the penalty-selection description is inconsistent. Physical testing provides preliminary evidence on two G1 tasks.

IllustratedReading report

JEPA Policy: Diffusion-Free Imitation Learning via Paired Action and Future Representation Prediction

Jie Xu; Kangjin Yu; Ziyi Jin +5 authors

9 Sept 2026

JEPA Policy trains a shared Transformer to predict an action chunk and the visual representation observed later in the same demonstration. Two deterministic passes refine both outputs. Its strongest evidence is improved simulated control relative to action-only MIP, supported by topology controls; future error also offers a delayed, task-dependent rollout diagnostic.

IllustratedReading report

Compact Visuotactile World Models for Lifting: Prediction, Reward Alignment, and Force Constraints

Qinzhen Ma; Sida Peng

WAMs Outside quadrants

9 Sept 2026

This study asks whether better contact prediction produces better lifting decisions. A compact visuotactile model improves forecasts over vision alone, but persistence challenges the value of its dynamics. An exploratory reward revision improves executed simulator lifting, while simple force feedback remains stronger under a force budget. A separate GelSight experiment exposes the gap between frame and trajectory reliability.

IllustratedReading report

Valerant: An Automatic Navigable Game Map Generator via Action-Conditioned World Model Exploration

Yiran Qiao; Feng Wang; Jing Ma

Related resources Not applicable

8 Sept 2026

Valerant expands one game screenshot into a persistent 3D point-cloud map by generating alternative action-conditioned videos, reconstructing each with SLAM, and committing the best admissible branch. A frozen video model supplies futures; an external exploration policy selects actions. Perceptual comparison and qualitative ablations support this prototype, while geometric reliability and reproducibility remain incompletely measured.

IllustratedReading report

SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators

Yuncong Yang; Zhengtao Han; Furkan Ozyurt +6 authors

WAMs Outside quadrants

8 Sept 2026

SyncWorld interprets robot commands through a short visual calibration context, then predicts proposed actions’ consequences with a video diffusion model. Calibration-conditioned training and distillation also support history-only prediction. It improves held-out video metrics and selected LIBERO policy outcomes, but the evidence is strongest for short-horizon simulation: ranking quality, object interactions and unseen-embodiment controllability remain limiting factors.

IllustratedReading report

WorldAgen: Unified State-Action Prediction with Test-Time World Model Training

Chi Wan; Kangrui Wang; Yuan Si +2 authors

8 Sept 2026

WorldAgen shares a Transformer between action prediction and future-observation prediction, then adapts the shared representation using exploratory target-environment transitions. Simulated manipulation improves after observation-only test-time training (TTT), while implementation ambiguities and unreported uncertainty limit the strength of the generalization claim.

IllustratedReading report

OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining

Yuran Wang; Siqiao Huang; Mingleyang Li +21 authors

7 Sept 2026

OpenWAM turns world–action modeling into a modular design study, then instantiates OpenWAM-α: a video DiT coupled to a dedicated ActionDiT through mutual attention and joint denoising. Its strongest lesson is conditional: embodied pretraining improves scene transfer, but strong manipulation scores coexist with substantial visual-robustness failures. The evidence below separates controlled ablations, final-model benchmarks and physical execution.

IllustratedReading report

Beyond Task Success: Stage-Wise Reliability of World Model Planning under Sensing Degradation

Geonmyeong Lee; Byoung-Tak Zhang

Evaluation metrics Not applicable

7 Sept 2026

This diagnostic study follows synthetic sensing disturbances through an existing world-model planner's representation, action-conditioned prediction, candidate ranking, and executed task outcome. Paired OGBench evaluations show that a disturbance's relative impact can change between stages. Temporal information position matters even when aggregate representation shifts are similar. These diagnostics locate sensitivity; they neither establish a general predictor of task failure nor demonstrate successful sensing mitigation.

IllustratedReading report

WM-Craftnet: World Synesthesia Model for Generalizable and Robust Dexterous In-Hand Manipulation

Jie Yin; Zeyuan Zhao; Xiaojing Tan +3 authors

WAMs Outside quadrants

7 Sept 2026

WM-Craftnet learns a predictive visuotactile state that conditions a separate dexterous manipulation policy. Its main contribution is recurrent perception for executed control: noisy depth, touch, proprioception, and action history inform a latent state trained with clean-depth and other prediction targets. Hardware rotation improves substantially, but severe-disturbance recovery remains limited (e-rssm, e-policy, e-stress).

IllustratedReading report

Learning to Use Imagination: Progress-Conditioned Future Utilization for World Action Models

Yijie Zhu; Zitong Yu; Wei Li +4 authors

6 Sept 2026

ProWAM learns execution progress from recent action–observation feedback and recurrent memory, then uses that state to redistribute imagined-future attention inside a joint video–action policy. Its strongest evidence combines executed manipulation results with ablations separating progress estimation from future utilization.

IllustratedReading report

How to Learn from What a Human Would Avoid? Intervention-Aware World Models with Real-World RL for Dexterous Manipulation

Jiaju Yin; Zhenhui Zhang; Lixin Xu +5 authors

WAMs Outside quadrants

5 Sept 2026

WHIRL learns when a human would take over a dexterous robot and uses that prediction to steer residual-policy training. A frozen imitation prior supplies nominal behavior; an action-conditioned, one-step latent world model supports critic learning and actor risk shaping. Five real-robot tasks show higher autonomous success, but the evidence is restricted to one training seed, one operator and familiar workspace regions.

IllustratedReading report

Learning Counterfactual World Models for Embodied Reasoning under Partial Observability

Todd Y. Zhou; Daniel Zhang

WAMs Outside quadrants

5 Sept 2026

Counterfactual Latent World Models (CLWM) train action-conditioned imagined futures to preserve differences in intervention outcomes even when observations look alike. A recurrent world model supplies latent rollouts to model-predictive control; privileged outcome labels supervise an additional contrastive objective during training. Reported simulation gains reach 11.6 percentage points in navigation success. The evidence supports targeted representation training, while supervision-matched controls and audits of pretrained encoders remain open.

IllustratedReading report

GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation

AgiBot Research Team

4 Sept 2026

GE-Act 2.0 connects a compact visual representation, a one-step future generator, and a separate inverse dynamics model. Its central training problem is pairing generated futures with compatible recorded actions. KASO selects futures using the current action model before updating both modules. Real-robot experiments show broader manipulation capability as co-training data grows, with persistent weaknesses in fine manipulation and ordinal language; simulation comparisons use a separate adaptation protocol.

IllustratedReading report

TacPAC: Tactile Prediction and Real-Time Action Correction in World-Action Models for Contact-Rich Manipulation

Zipei Ma; Xiaofei Wei; Junzhe Jiang +2 authors

4 Sept 2026

TacPAC predicts future visual and tactile observations while planning an action chunk, then uses incoming touch to revise its unfinished actions against a fixed prediction-and-plan cache. On five physical manipulation tasks, it reports 64% average success versus 48% for T-Rex and 22% for its vision-only ablation. The central evidence is the controlled cache-access ablation, not visual prediction quality alone.

IllustratedReading report

TourPhysics: Bringing Physics to World Models for Exploration and Manipulation from a Single Image

Xin Zhang; Yabo Chen; Zixuan Duan +4 authors

Benchmarks & simulators Not applicable

4 Sept 2026

TourPhysics renders persistent camera tours and object manipulations from a single image plus a declared physical scene. A simulator fixes each trajectory before diffusion generates its appearance; accepted windows publish physical endpoints and visual memory together. The strongest evidence concerns prescribed motion and modest improvements on held-out revisits, with limited physical-event support and no real-world validation.

IllustratedReading report

GIFT: Guided Intermediate Feature Training via Action-Oriented Structural Supervision for Robotic Manipulation

Yupeng Zheng; Xiang Li; Songen Gu +11 authors

3 Sept 2026

GIFT trains robot-policy features to retain geometry, object–end-effector relations and instruction-relevant regions. The same auxiliary objectives improve three different action formulations while their default deployment uses no auxiliary predictions. Evidence is strongest for matched-baseline robustness gains, with substantial annotation requirements and uneven benefits across shifts.

IllustratedReading report

Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Models

Shaunak A. Mehta; Ananya Hazarika; Haochen Zhang +5 authors

Related resources Not applicable

3 Sept 2026

This survey organizes robot learning around representations that encode the environment, VLA policies that generate actions, and world models that predict consequences. Its useful contribution is a vocabulary for tracing how information and feedback cross those interfaces. Integration can remain modular; the authors argue that its value should be demonstrated through improved behavior under uncertainty, distribution shift and temporal dependencies. A small original CALVIN video-prediction diagnostic illustrates hidden-object and collision failures, but supplies no quantitative proof that a unified architecture resolves them.

IllustratedReading report

WISE: World-model-guided Imagination Scheduling for Efficient Post-training of Vision-Language-Action Models

Chenhao Zhang; Hanyu Zhao; Hang Cheng +2 authors

WAMs Outside quadrants

3 Sept 2026

WISE post-trains a VLA action head by selectively imagining alternative behaviors at visually identified interaction states. A separate frozen world model predicts bounded futures; a frozen evaluator ranks them; updates supervise only the first action chunk from a real context. The strongest controlled evidence is the scheduling ablation: higher task success with substantially less imagination computation. The method, results, and reproduction boundaries below trace this conclusion to the primary text.

IllustratedReading report

SV-WAM: An Efficient Surround-View World-Action Model for End-to-End Autonomous Driving

Jinyang Wang; Shiwei Li; Junjian Wang +12 authors

3 Sept 2026

SV-WAM trains one shared transformer to denoise driving actions and future surround-view video, but blocks action attention to future-video tokens. Deployment retains six-camera history while generating only trajectories. A differentiable vehicle-footprint loss improves road compliance. The strongest reported result is 91.0 EPDMS on NAVSIMv2 navtest; the evidence concerns benchmark planning, with weaker hard-split performance and no demonstrated real-vehicle deployment.

IllustratedReading report

Drive-HWM: Hierarchical World Models for Dynamic-Latent Guided Autonomous Driving

Zhaoxin Fan; Tianbao Zhang; Wenjun Wu +5 authors

3 Sept 2026

Drive-HWM couples a periodically refreshed predictor of future motion latents with an observation-grounded autoregressive driving policy. Optical flow supervises the slow branch; next-frame RGB tokens supervise the fast branch during training. NAVSIM tables report stronger aggregate driving scores, but conflicting prose and incomplete implementation details limit precise reproduction.

IllustratedReading report

Toward Physically Grounded JEPA World Models for Goal-Conditioned Robotic Planning

Muyuan Liu; Yue Huang; Zheng Liang +1 authors

WAMs Outside quadrants

3 Sept 2026

SA+IDM trains an action-conditioned JEPA world model with two auxiliary heads: inverse dynamics recovers executed actions, while state alignment predicts measured physical state from consecutive image representations. Deployment uses only the encoder and latent predictor inside CEM planning. State alignment improves all four reported tasks over IDM alone, while the diagnostics challenge average temporal straightening as a sufficient representation-quality criterion (e2–e12).

IllustratedReading report

Building Pretraining Data for World Models: An Unreal Engine-Based Pipeline for Action-Conditioned Video Generation

Haoyu Wang; Songchun Zhang; Haoran Li +3 authors

Datasets Not applicable

3 Sept 2026

This paper documents the Unreal Engine synthetic-data component used in EchoWM: simulate character motion once, record controls and states, then replay the trajectory for high-quality multi-view rendering. Its contribution is a production system combining scene curation, cache locality and failure recovery. Reported video volume establishes production scale; downstream learning utility remains untested here. [e-scope, e-workflow, e-scale, e-limits]

IllustratedReading report

Latent Energy Action Planning with World Models

Phu Pham and Aniket Bera

WAMs Outside quadrants

3 Sept 2026

LEAP refines an action horizon through frozen LeWorldModel dynamics, combining latent-goal matching with a learned decoder’s terminal-state error. A trained proposal initializes search; projection bounds executed controls. Four-domain mean success rises from 77.5% to 94.8% against matched LeWM+CEM. The narrower energy ablation improves from 91.0% to 96.5%, separating the extra objective’s contribution from the complete planner change. Numerical goal descriptors and trustworthy learned rollouts remain prerequisites (e-energy, e-proposal, e-optimization, e-main, e-ablation, e-limits).

IllustratedReading report

Spatially Aware World Action Model via Geometric Latent Diffusion

Gonzalez, Javier Alejandro Lopetegui; Pacaud, Paul; Schmid, Cordelia

2 Sept 2026

To bridge this gap, we introduce a Spatially Aware World Action Model (SA-WAM), which repurposes a pretrained video model for joint action, RGB, and depth prediction, enabling 3D-aware world modeling and action prediction within a single diffusion backbone. SA-WAM achieves state-of-the-art results on the RoboCasa and LIBERO-Plus benchmarks, while simultaneously improving future-state predictions.

IllustratedReading report

World-Coherent Decoding: Self-Verifying Test-Time Planning for World Action Models

Zhang, Chuhan; Ito, Seiji; Hoshino, Kenta +2 authors

WAMs Outside quadrants

2 Sept 2026

We propose World-Coherent-Decoding (WCD), a self-verifying test-time planning framework that treats WAM rollouts as falsifiable future--action hypotheses.

IllustratedReading report

Latent Action as Intention Enables Efficient Future Imagination for World Action Models

Li, Xiang; Zheng, Yupeng; Gu, Songen +11 authors

1 Sept 2026

To bridge this gap, we introduce LAWA, a WAM architecture that uses compact latent actions as an operational representation of future intentions, enabling efficient test-time future imagination without generating future observations. On RoboCasa, LAWA achieves state-of-the-art average success rates of 65.6% and 80.8% in the few-shot and full data settings, improving over the matched Fast-WAM baseline by 9.6 and 4.5 points, respectively.

IllustratedReading report

ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training

Wu, Xionghao; Yang, Yijun; Zhou, Shiyang +17 authors

31 Aug 2026

We introduce ZimaBlue, a scalable framework for learning generalizable World Action Models (WAMs) from large-scale video.

IllustratedReading report

Motus2: A Self-Evolving General World Model for Dexterous Manipulation

Bi, Hongzhe; Zhou, Zihao; Tang, Yihang +16 authors

WAMs Outside quadrants

31 Aug 2026

We present Motus2, a self-evolving general world model for dexterous manipulation.

IllustratedReading report

DELE-w0.5: Inferring Action from Future Latent State for Robotic Manipulation

Lei, Fenghao; Huang, Zhixiong; Yang, Long +5 authors

31 Aug 2026

In this paper, we propose DELE-w0.5, which infers robot actions from predicted future states without relying on video generation. Across 640 real-robot trials on four long-horizon manipulation tasks, our DELE-w0.5 achieves the best performance among all compared policies, attaining 62.5% overall full-task success and 81.3% macro ordered-stage progress.

IllustratedReading report

AcrossWAM1.0:A Modular Latent World-Action Stack for Compact Robot Policies

Zhang, Yafei; Wu, Nan

30 Aug 2026

We introduce AcrossWAM1.0, a modularization and scaling study of this latent world-action stack.

IllustratedReading report

Flex-ππ: A Multi-Stream World-Action Model with Compute Flexibility

Yan, Ge; Liu, Jinghao; Fan, Yuzhi +4 authors

29 Aug 2026

World-action models (WAMs) predict the future to act better, but nearly all of them predict only RGB latents, trained purely for pixel reconstruction, with no explicit signal for the 3D geometry or object semantics manipulation needs. We find a surprising free lunch: the same frozen video-generation VAE that encodes RGB also encodes 3D pointmaps almost losslessly, with no pointmap-specific training at all.

Paper Code Project

IllustratedReading report

Hydra: A Navigation World Action Model with Discrete Latent Planning and Continuous Flow-Matching Execution

Nazeri, Mohammad; Card, Alexandyr; Huber, Samira +6 authors

WAMs Outside quadrants

28 Aug 2026

In this paper, we present Hydra, a discrete World Action Model that closes this gap by moving the planner, both the sampler and the evaluator, inside the model. Evaluated on two physical robotic platforms, Hydra outperforms state-of-the-art world models in goal-directed planning, while matching or exceeding the closed-loop execution capabilities of leading reactive foundation policies.

IllustratedReading report

Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models

Yang, Senqiao; Wang, Chengyao; Chen, Yuxin +13 authors

VLA Not applicable

27 Aug 2026

We propose VLAct, a VLA-oriented VLM backbone trained on broad, heterogeneous, multi-embodiment robot data before task-specific fine-tuning. On RoboDojo, VLAct ranks sixth among all policies by success rate and outperforms all explicitly designated world-action model (WAM) entries on both metrics.

Paper Code Project

IllustratedReading report

Making Latent Evolution Explicit: Operator-Structured Transitions for World Action Models

Lu, Xiaoxiao; Dong, Yunlong; Shi, Jiahao +1 authors

WAMs Outside quadrants

27 Aug 2026

We introduce the Latent Evolution Operator Network (LEON), which models latent evolution in a learned observable space through context-modulated operator-based propagation and additive forcing.

IllustratedReading report

Riemann-1.0: An Embodied World Action Model for Physical AI

Sun, Haofeng; Pei, Jiangbo; Kang, Fei +13 authors

WAMs Outside quadrants

27 Aug 2026

We introduce Riemann-1.0, a fully causal autoregressive World Action Model for embodied intelligence. Riemann-1.0 achieves state-of-the-art performance across both simulation benchmarks and real-world manipulation tasks.

IllustratedReading report

Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization

Zhou, Jiaming; Zhang, Qihang; Xu, Gangwei +9 authors

27 Aug 2026

To achieve cross-task generalization, we bring this paradigm to robotic manipulation, and argue that the natural task specification for manipulation is a human video: unlike language, it provides rich visual cues about the intended task evolution. We present Zero-WAM, a causal video-action model that executes unseen tasks by following in-context human video guidance.

IllustratedReading report

Tactile-WAM: Touch-Aware World Action Model with Tactile Asymmetric Attention

Wu, Siyu; You, Linjing; Zhu, Junjie +9 authors

27 Aug 2026

On five real-robot tasks, Tactile-WAM achieves 49.2% success.

IllustratedReading report

4DGS-WAM: Bridging Past and Future with an Object-Centric World Action Model based on 4D Gaussian Splatting

Ma, Yueen; Xu, Zenglin; King, Irwin

WAMs Outside quadrants

26 Aug 2026

These models can achieve exceptional visual quality, but they lack explicit spatial structure for individual objects and repeatedly process redundant background content.

IllustratedReading report

SimWAM: A Simple World Action Model for End-to-End Autonomous Driving

Zhao, Zongchuang; Zhou, Xin; Xu, Tianyang +6 authors

WAMs Outside quadrants

26 Aug 2026

We present SimWAM, a simple yet effective WAM that leverages future-video prediction as a training-time supervision signal. Our SimWAM achieves 91.5 PDMS on NAVSIM, surpasses state-of-the-art WAM-based planners with substantially lower latency, and transfers zero-shot to nuScenes.

IllustratedReading report

From World Models to World Action Models: A Concise Tutorial for Robotics

Zhang, Xiaoxiong; Zeng, Xiong; Zhang, Wei

Related resources Not applicable

26 Aug 2026

Rather than providing an exhaustive survey, this paper presents a concise tutorial on world models and world action models for robotics.

Paper Code Project

IllustratedReading report

SANTS: A State-Adaptive Scheduler for World Action Models

Sun, Yirui; Zhuge, Guangyu; Liu, Keliang +5 authors

26 Aug 2026

We introduce State-Adaptive Noise Trajectory Scheduler (SANTS), a lightweight scheduler for video-to-action diffusion policies.

IllustratedReading report

GameWAM: A World Action Model for Video Games

Guo, Yuncheng; Zhang, Zhanqiu; Guo, Yiwen +1 authors

25 Aug 2026

We introduce GameWAM, to our knowledge the first WAM for native closed-loop gameplay and GUI control.

IllustratedReading report

GaussianWAM: Distilling Geometry and Semantics from 3D Gaussian Fields into World-Action Models

Zhang, Zijian; Jiang, Yuqing; Zhou, Weitao +6 authors

WAMs Outside quadrants

25 Aug 2026

We propose \textbf{GaussianWAM}, a training-time representation-enhancement framework that organizes geometric and semantic supervision through a 3D Gaussian field.

IllustratedReading report

GeoWAM: Visual Geometry World Action Models for Autonomous Driving

Lu, Yiren; Ye, Xin; Liu, Jiaming +10 authors

25 Aug 2026

Building on this insight, we introduce \textbf{GeoWAM}, a visual geometry world action model for autonomous driving.

IllustratedReading report

GlanceWAM: Sparse Test-Time Imagination for World-Action Models

Wang, Linhan; An, Zijian; Zhang, Mingyuan +7 authors

24 Aug 2026

We show that visual imagination achieves both real-time inference and superior success rates when generated asynchronously off the critical path and consumed directly in latent space. We introduce GlanceWAM, which decouples imagination from control within a single video DiT: an asynchronous proposer glances ahead on a slow clock to imagine a single lookahead frame seconds into the future in the background, while an action head decodes action chunks at control rate (48 ms) purely in latent space without blocking.

IllustratedReading report

ReWorld: Representation Learning for World Action Models

Xia, Tianze; Zhou, Lijun; Xiong, Kaixin +8 authors

24 Aug 2026

We present ReWorld, the first representation learning framework specifically designed for autonomous-driving WAMs.

Paper Code Project

IllustratedReading report

LD4WAM: Learning Latent Dynamics from Human Videos for World Action Models

Shen, Zhenhao; Liang, Jiaqi; Lu, Jasper +11 authors

23 Aug 2026

Human video is playing an increasingly central role in training World Action Models (WAMs), owing to its diversity and low collection cost relative to teleoperated robot data. However, most WAMs learn from such video only by predicting pixel-level future frames, giving dynamics that are not directly actionable, whereas motion retargeting recovers directly actionable actions but leaves a large visual gap across embodiments.

IllustratedReading report

WAM-OPD: On-Policy Distillation for World Action Models

Yang, Liuhaichen; Jiang, Zhuang; Sheng, Chenchao +1 authors

23 Aug 2026

We introduce WAM-OPD, a deployment-consistent post-training recipe for a video-first WAM.

IllustratedReading report

ForeTime-VLA: Causal Future-Token Distillation from a World Action Model for Conveyor-Belt Manipulation

Ma, Siyuan; Zhang, Yutian; Zhang, Boshi +4 authors

23 Aug 2026

We introduce ForeTime-VLA, a dense pi0.5 policy that distills a future-aware, action-equivalent representation from a frozen Fast-WAM-derived teacher while remaining causal at inference. In quantitative real-robot evaluation, ForeTime-VLA achieves 81.1% stationary and 58.9% slow-moving grasp success, exceeding the next-best reference by 12.2 and 22.2 percentage points, respectively.

IllustratedReading report

TacWAM: Anchor-Guided World Action Model with Mechanics-Aware Tactile Prediction

Jin, Lei; Ma, Yiding; Zhang, Xin +3 authors

WAMs Outside quadrants

23 Aug 2026

We present TacWAM, a mechanics-aware tactile WAM that addresses this challenge in three steps. TacWAM achieves an average success rate of 75.0%, exceeding the strongest evaluated baseline by 37.5 percentage points.

IllustratedReading report

On the Capability Separation Between World-Model Policy Learning and Imitated World-Action Models

Yu, Yang

Related resources Not applicable

22 Aug 2026

World-action models predict a future outcome and then infer an associated action. Although this factorization can improve representation learning and data efficiency, it is unclear whether it provides stronger control capability than direct behavior cloning when both are trained from the same observational demonstrations.

IllustratedReading report

WA-JEPA: Rethinking the Video JEPA Paradigm for World-Action Modeling in Autonomous Driving

Wang, Xinlin; Xiang, Yujiao; Zhou, Yuheng +11 authors

21 Aug 2026

Video Joint Embedding Predictive Architecture (V-JEPA) learns powerful spatiotemporal representations from video through self-supervised latent feature prediction. However, V-JEPA is built around random-mask completion and deterministic regression, making it fundamentally ill-suited for autonomous driving planning that demands future-directed prediction tightly coupled with action.

Paper Code Project

IllustratedReading report

DECOWAM: Decoupled Whole-Body World-Action Model for Legged Mobile Manipulation

Ma, Siyuan; Zhang, Boshi; Zhang, Yutian +4 authors

WAMs Outside quadrants

21 Aug 2026

Here we introduce DECOWAM, a whole-body world-action model that separates these factors through dedicated conditional interfaces.

IllustratedReading report

Towards Surgical World-Action Modeling: A Preliminary Joint Visual-Trajectory Forecasting for Surgical Motion Planning

Huang, Weiliang; Liu, Huanrong; Zhang, Bob +5 authors

20 Aug 2026

To bridge this gap, we present a preliminary joint visual-trajectory world-action model that simultaneously forecasts future visual states and instrument trajectories from historical surgical observations. The chunked strategy consistently outperforms direct one-shot prediction across all evaluated horizons, improving first-segment PSNR from 18.86 to 23.11 dB and reducing ADE from 45.77 to 22.22 pixels.

IllustratedReading report

What Matters for Latent Actions in Robot Learning

Xizhou Bu; Qingda Hu; Lei Zhou +13 authors

20 Aug 2026

This empirical study asks which video-derived latent actions improve robot policies. It compares modeling paradigms, regularization, and action integration under a shared training framework. Raw-frame LAPO remains competitive, but preferred dimensionality and action heads depend on the evaluation. Its strongest deployment evidence is improved Franka manipulation after latent-action tuning of a VLM backbone; the forward predictor supplies training supervision rather than an inference-time planner.

IllustratedReading report

RISE: Adaptive Imagination for World Action Models

Lu, Hongbo; Yao, Liang; He, Chenghao +5 authors

WAMs Outside quadrants

19 Aug 2026

We propose RISE (\textbf{R}efining \textbf{I}magination through \textbf{SE}lective Rollout), a system-level adaptive imagination framework that makes sequential \textsc{Roll}/\textsc{Stop} decisions according to the expected planning benefit of continued rollout. Experiments on NAVSIM and nuScenes show that RISE achieves the best overall planning performance while reducing unnecessary rollout, with additional transfer results supporting its plug-in generality across WAM architectures.

Paper Code Project

IllustratedReading report

HiTac-WAM: A Hierarchical Tactile World Action Model for Contact-Rich Robot Manipulation

Xue, Chao; Zhang, Chaofan; Ma, Wenxuan +3 authors

WAMs Outside quadrants

19 Aug 2026

We present HiTac-WAM, a hierarchical tactile world action model that forecasts a sequence of future tactile states for each candidate action chunk before execution. HiTac-WAM achieves a mean contact F1 of 0.921; under matched training budgets, the directed hierarchy reduces 3D displacement L2 error by 17.6% relative to the deformation-only predictor and improves slip AUPRC by 60.4% relative to the slip-only predictor.

IllustratedReading report

BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving

Zhan, Bing; Shang, Shuyao; Lu, Shuo +6 authors

19 Aug 2026

Inspired by neuroscience evidence that complex behavior arises from coordination among functionally specialized systems, we propose BrainWAM, a structured action-space coordination framework that converts semantic reasoning and predictive world modeling into two specialized action-oriented pathways, and aligns them at the level of compact action representations. BrainWAM reaches state-of-the-art performance on both NAVSIM v1 (89.5 PDMS) and NAVSIM v2 (89.6 EPDMS), consistently outperforming VLA-only or WAM-only methods, highlighting BrainWAM as a practical and promising direction for autonomous driving systems.

IllustratedReading report

WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLN

Huang, Yuehao; Wu, Yunzi; Zhang, Xiaotao +7 authors

19 Aug 2026

We present WNM-3D, a generative World Navigation Model with 3D scene conditioning for continuous VLN. Experiments on GN-Bench show that WNM-3D outperforms strong VLM-based navigation policies and its 2D-conditioned counterpart in closed-loop navigation.

Paper Code Project

IllustratedReading report

Hydra-0: Action Flow for Generalist World Modeling and Control

Li, Hongyu; Wen, Bowen; Zhu, Xinghao +8 authors

18 Aug 2026

We introduce Hydra-0, a generalist world model conditioned on action flow, which represents robot actions as pixel motion. Our best configuration achieves 90.4% lower robot-motion error and 60.2% lower object-motion error than our action-conditioned baseline, while supporting zero-shot composition and data-efficient adaptation.

IllustratedReading report

Teach and Grow: An Agent-Centered Architecture for General Robot Learning

Nie, Chang; Liu, Zhe; Wang, Hesheng

Related resources Not applicable

17 Aug 2026

We present Teach-and-Grow Learning (TGL), an agent-centered architecture for general robot learning. Our LIBERO evaluation attains state-of-the-art performance; controlled studies expose skill induction, persistent reuse, and agent-directed adaptation.

IllustratedReading report

StageWAM: Joint-Embedding Stage Prediction for World-Action Models in Robot Manipulation

Liu, Xiao; Yang, Yuguang; Wang, Xi +6 authors

14 Aug 2026

We introduce StageWAM, which augments a Motus-based World Action Model (WAM) with Stage-JEPA, a goal-conditioned Joint-Embedding Predictive Architecture (JEPA) predictor. Across 50 RoboTwin 2.0 tasks in clean and randomized environments, StageWAM achieves 90.25% overall success and reduces the mean number of execution steps in successful rollouts by 5.97% relative to the strongest baseline.

IllustratedReading report

PhyAI: Real-Time Physical AI at the Edge, Scalable Rollouts in the Cloud

Chenghua Wang; Daliang Xu; Dongqi Cai +23 authors

Related resources Not applicable

14 Aug 2026

To unify them, we build PhyAI, a Physical AI inference engine with a single runtime that keeps architecture-specific conditioning, solver, cache, and output logic in model adapters while sharing graph execution, kernels, memory management, and parallel services. PhyAI achieves 1.40x-4.65x speedups over the official implementations of pi0, pi0.5, GR00T N1.7, and MiniCPM-Robot.

IllustratedReading report

RoboSynChallenge: Mastering Real-World Dexterity via Generalizing Synthesized Manipulation Skills

Zhao, Runyi; Wu, Ruixin; Li, Chengkun +15 authors

Benchmarks & simulators Not applicable

12 Aug 2026

Achieving generalizable robotic manipulation remains a central challenge in embodied intelligence. Despite rapid advances in model architectures and learning algorithms, progress is often limited by the scarcity and narrow diversity of real-world data.

Paper Code Project

IllustratedReading report

Keep the Future, Drop the Rollout: RIFT for World Action Models

Zhang, Chushan; Tong, Jinguang; Li, Xuesong +2 authors

12 Aug 2026

On LIBERO, RIFT achieves 98.8%98.8\% success, close to rollout-based Joint, IDM, and LingBot-VA at 98.4%98.4\% to 98.6%98.6\%, while reducing action-chunk latency by 68.2%68.2\% to 89.1%89.1\%.

IllustratedReading report

4D-WAM: Infusing Spatiotemporal Awareness into World Action Models through Trajectory Fields

Yang, Lishan; Song, Wenxuan; Wang, Xi +14 authors

WAMs Outside quadrants

12 Aug 2026

In this work, we propose 4D-WAM, a model-agnostic training strategy that injects spatiotemporal knowledge from 3D trajectory fields into WAMs through representation alignment. To this end, we introduce two complementary objectives: 1) motion alignment, which aligns temporal feature variations across adjacent frames and encourages the model to build local 4D awareness during training, and 2) destination alignment, which guides the model to infer the final destination from the source frame by minimizing the gap between their attention-like similarity distributions.

IllustratedReading report

Foresight Without Seeing: Latent Futures for World Action Models

Huang, Jiakai; Wu, Zhongbo; Zhang, Zheng +3 authors

11 Aug 2026

To bridge this gap, we propose ForeWAM, a dynamics-conditioned direct-policy WAM that provides predictive context for action generation without decoding future videos. Without embodied robot data pretraining, the standard and accelerated variants of ForeWAM achieve average success rates of 96.7% and 96.9% on LIBERO, respectively.

IllustratedReading report

Surgical WAM: A World-Action Model for Data-Efficient Surgical Robot Learning

Bao, Wenrui; Jiang, Tianyun; Chen, Zhiben +3 authors

11 Aug 2026

To answer it, we introduce the Surgical World-Action Model (Surgical WAM), a unified generative model built on Cosmos Policy that jointly predicts future endoscopic observations and executable surgical robot action chunks.

IllustratedReading report

World Action Models in Real Time: An Empirical Study of Smooth Execution via Asynchronous Deployment

Team, Motubrain

Related resources Not applicable

11 Aug 2026

We present an empirical study of asynchronous deployment strategies that overlap model inference with action execution to enable responsive and smooth control. In contrast, prefix-conditioned generation achieves the best overall balance between task performance, execution speed, and trajectory smoothness by learning consistent action continuations during training.

IllustratedReading report

FACT: Failure-Aware Causal Training for World-Action Models

Peng, Quanquan; Liang, Yutong; Yan, Rui +2 authors

WAMs Outside quadrants

10 Aug 2026

We introduce FACT, a causal World-Action Model that predicts future video and task progress conditioned on the executed action. Extensive experiments on simulation and real-world bimanual manipulation tasks show that FACT outperforms many existing baselines, improves as failure data are incorporated into training, and reduces success-biased future hallucination under bad actions.

Paper Code Project

IllustratedReading report

4D-WAM: 4D Consistent World Modeling for Autonomous Driving

Fu, Jiacheng; Yuan, Yibo; Tian, Meng +8 authors

10 Aug 2026

To alleviate this issue, we present 4D-WAM, a model that leverages geometric foundation models for training-time supervision to enable 4D consistent world modeling. Extensive experiments demonstrate that 4D-WAM effectively models 4D consistent scene evolution and achieves state-of-the-art performance on challenging NAVSIM-v1 and NAVSIM-v2 benchmarks.

IllustratedReading report

SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulation

Wang, Jingkai; Tang, Zihan; Zhang, Gu +7 authors

VLA Not applicable

10 Aug 2026

We propose SLIM (Self-supervised Latent Interaction Model), a compact 0.5B-parameter latent interaction policy.

Paper Code Project

IllustratedReading report

World Tokens: Enhancing Embodied Policies with Training-Time World Modeling

Tang, Qu; Zhuang, Benhui; Yuan, Bo +3 authors

WAMs Outside quadrants

10 Aug 2026

We introduce World Tokens, an embodied policy architecture built around a World Adapter that bridges visual-language understanding, world-dynamics modeling, and action generation.

IllustratedReading report

HarnessWAM: Bridging Prediction and Deliberation in World Action Models

Gu, Zhaopeng; Zhu, Bingke; Lin, Tianxi +8 authors

WAMs Outside quadrants

10 Aug 2026

To address this gap, we propose HarnessWAM, an agentic framework for WAMs. HarnessWAM achieves state-of-the-art full-task and subtask success rates of 59.6% and 69.9% on RoboMemArena, and an SR of 23.7% on RoboCerebra Ideal.

IllustratedReading report

Rethink Before You Execute: Adaptive Execution for World Action Models

Ye, Feng; Zhao, Yiming; Yu, Yong +5 authors

WAMs Outside quadrants

10 Aug 2026

We propose TempoWAM (Timing Execution by Monitoring Progress Online), a lightweight plug-and-play execution scheme for WAMs.

IllustratedReading report

JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling

Lin, Yihan; He, Jiawei; Bao, Shifeng +6 authors

WAMs Outside quadrants

10 Aug 2026

We introduce JEPA-WAM, a latent WAM built in a pretrained V-JEPA space, which couples latent transition prediction with continuous action generation through a shared predictor. On LIBERO-Plus, JEPA-WAM achieves 79.2%, the best result without large-scale robot-policy pretraining, while its pretrained π0.5π_{0.5} instantiation reaches 86.3%, achieving the best overall performance.

Paper Code Project

IllustratedReading report

SG-WAM: Text-Grounded and Spatial-aware Semantic Guidance for World-Action Models

He, Junjie; Li, Junfeng; Zhong, Zhide +9 authors

9 Aug 2026

To overcome this limitation, we propose SG-WAM, a semantic guidance method for world-action models that leverages a vision-language model (VLM) as a semantic planner to enhance the instruction-grounding capacity of world-action models.

IllustratedReading report

Vid2WAM: Distilling Video Diffusion Priors into World Action Models

Qiu, Chenhao; Wang, Ruixiang; Zhao, Runyi +7 authors

WAMs Outside quadrants

9 Aug 2026

In this paper, we propose Vid2WAM, an offline distillation framework that transfers visual diffusion priors from a large video foundation model into a compact WAM student. To robustly integrate synthetic and real supervision, we introduce source-aware residual action adaptation that learns source-specific corrections around a shared action backbone and mitigates interference from noisy pseudo-actions.

Paper Code Project

IllustratedReading report

ω-0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation

Li, Zhe; Zhang, Zhenzhe; Wei, Yangyang +8 authors

9 Aug 2026

We present ωω-0, a latent predictive whole-body world-action model for real-world humanoid concurrent loco-manipulation. Real-world experiments on 11 household tasks demonstrate that a single ωω-0 model can produce smooth manipulate-while-moving behaviors and consistently outperform representative imitation learning, VLA, humanoid, and WAM baselines.

IllustratedReading report

Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots

Xu, Ling; Li, Borui; Wu, Hao +8 authors

Related resources Not applicable

9 Aug 2026

We present Embodied..cpp, a portable C++ inference runtime for embodied models. Overall, Embodied..cpp achieves 1.05x-2.70x inference speedups and 7\%-77\% lower VRAM relative to Python baselines, while maintaining near-baseline success for most configurations.

IllustratedReading report

Data Pyramid for Embodied Manipulation: A Survey

Yifan Ye; Yankai Fu; Yaoxu Lv +26 authors

Related resources Not applicable

8 Aug 2026

Multimodal foundation models learned to see and to speak by consuming the whole internet. Embodied agents admit no such shortcut, since they require data that couple observations with physical states and actions.

Paper Code Project

IllustratedReading report

Selective Cross-View Consistency for World Action Models: Held-Out Viewpoint Robustness Without Test-Time Camera Information

Huang, Bingqi; Wei, Bingchuan; Cai, Yingkai +1 authors

7 Aug 2026

We introduce a carve-and-hold-out evaluation protocol on the LIBERO-Plus camera track that separates a distribution-matched ceiling from genuine interpolation and extrapolation to held-out viewpoints, with a matched pair-trained control isolating the effect of the consistency term from pair exposure.

IllustratedReading report

Decoupling Intention from Trajectory: A Representational Deduction Framework for World Action Models

Ma, Xiangkai; Ma, Yue; Wang, Junjie +6 authors

7 Aug 2026

We propose PILOT (Physical Inference for Latent Optimized Trajectories), whose core Representational Deduction (RD) bridges this gap by integrating motion thought-of-chain (CoT) guidance as a native model capability.

IllustratedReading report

Robust-WAM: Bridging Generative Pretraining and Semantic Foresight in World-Action Models

Yan, Haodong; Li, Junfeng; He, Junjie +12 authors

WAMs Outside quadrants

7 Aug 2026

To overcome this dilemma, we propose Robust-WAM, a general post-training method for video-generation-based WAMs that preserves the VAE-based generative path and adds a lightweight semantic foresight alignment objective on the action stream.

Paper Code Project

IllustratedReading report

Adaptive-WAM: Quality-Guided Early-Exit Planning from Intermediate Video-Diffusion Features

Ang, Sining; Yang, Yuguang; Wang, Yan

6 Aug 2026

Based on this observation, we introduce Adaptive-WAM, a quality-aware multi-exit planner built on a Wan2.2-5B backbone. On NAVSIM, the adaptive single-trajectory planner achieves 90.8 PDMS; a separate fixed-exit variant reaches 92.6 PDMS with 64 proposals.

IllustratedReading report

MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresight

Fan, Zehua; He, Junjie; Song, Wenxuan +14 authors

WAMs Outside quadrants

6 Aug 2026

MobileWAM surpasses state-of-the-art mobile manipulation policies on ManiSkill-HAB and fine-tunes to a real ARX Lift2 mobile manipulator across diverse tasks with strong generalization.

IllustratedReading report

DynamicWAM: Dual-Path Motion Conditioning for World-Action Models in Dynamic Manipulation

Lou, Yunfan; Gao, Hewen; Zhu, Xiyu +6 authors

6 Aug 2026

We propose DynamicWAM, a compact WAM for dynamic object manipulation with dual-path motion conditioning. On DOMINO, DynamicWAM achieves a 38.2% success rate and a 53.2 manipulation score, outperforming all evaluated baselines.

Paper Code Project

IllustratedReading report

DreamWAM: Beyond RGB Future Prediction for World Action Models

Yuan, Shanglin; Zhao, Weiheng; Shi, Xin +6 authors

5 Aug 2026

We introduce DreamWAM, which reformulates future prediction as structured world modeling beyond RGB, representing future states through complementary views of appearance, motion, geometry, and semantics.

Paper Code Project

IllustratedReading report

Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models

Zhao, Weiheng; Jiang, Haoyi; Shi, Xin +5 authors

4 Aug 2026

Specifically, we propose SparseMoT to replace ubiquitous layer-wise fusion with selective video-action interaction at a compact subset of network stages, and Interval KV-Fusion to aggregate multi-depth future representations without increasing attention complexity. Experiments demonstrate that Faster-WAM achieves a substantially better performance-efficiency trade-off than existing WAMs.

IllustratedReading report

LiLa-WAM: Lightweight Latent Reasoning World-Action Model for Robotic Manipulation

Yang, Fan; Su, Yuting; Wang, Xiaobo +7 authors

4 Aug 2026

In this work, we propose LiLa-WAM, a lightweight world-action model that reasons about the future in a compact latent space and can be trained end-to-end on a single 24GB GPU.

Paper Code Project

IllustratedReading report

UniNav: A Unified World-Action Diffusion Model for Visual Navigation

Zhou, Changqing; Luo, Yueru; Jiang, Zeyu +1 authors

4 Aug 2026

We present UniNav, a unified world-action model that generates future visual observations and continuous waypoint trajectories through a single diffusion process. Based on this unified framework, we introduce two variants: UniNav-Full jointly predicts interpretable future observations and their corresponding trajectories, while UniNav-Fast removes future-image tokens at inference for efficient trajectory prediction.

IllustratedReading report

CoWAM: Coordination Contracts for Selective Policy Intervention with WAMs

Liu, Shuaijun; Wen, Qifu; Hao, Shuyang +5 authors

WAMs Outside quadrants

3 Aug 2026

We present CoWAM, a selective intervention layer that expresses synchronization, role compatibility, and collision convergence as coordination contracts.

IllustratedReading report

Faster-WAM: Do World Action Models Need Deep Action Modules?

Ma, Liheng; Yang, Rui Heng; Zhang, Zhanguang +4 authors

WAMs Outside quadrants

3 Aug 2026

To address this limitation, we introduce Dock of Transformer (DoT), a video-centric design principle that treats a pretrained video Transformer as a representation hub and connects lightweight output-heads through docking interfaces. Without additional embodied pretraining, Faster-WAM achieves competitive performance on LIBERO and RoboTwin 2.0 while demonstrating strong out-of-distribution generalization on LIBERO-Plus.

IllustratedReading report

SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Space

Zhao, Ruiteng; Zhang, Zhengshen; Su, Yue +6 authors

WAMs Outside quadrants

2 Aug 2026

We propose SG-WAM, a self-guided framework that learns geometry-aware action-conditioned dynamics directly in the policy-derived representation space. Built on a 0.9B model without large-scale embodied pretraining, SG-WAM achieves 98.5% average success on LIBERO and 73% on LIBERO-Plus, while outperforming strong baselines in both in-distribution and out-of-distribution real-world evaluations.

IllustratedReading report

EndoWAM: A Grounded World-Action Model for Generalizable Endoscopic Navigation

Lin, Jinsong; Pan, Zikang; Liu, Wanhao +10 authors

2 Aug 2026

We present EndoWAM, which is, to our knowledge, the first WAM for generalizable robotic endoscopic navigation. EndoWAM consistently outperforms all baselines and alternative grounding strategies, while demonstrating strong zero-shot generalization to unseen viewpoints, environments, and targets.

IllustratedReading report

SelfWAM: A Self-Grounded Unified World Action Model for Fast Robot Control

Pan, Bikang; Liu, Fan; Lu, Haotao +2 authors

WAMs Outside quadrants

1 Aug 2026

We introduce SelfWAM, a unified self-grounded WAM built on a modality-specialized Mixture-of-Transformers (MoT) architecture that jointly predicts actions, action-conditioned future RGB frames, and robot self-masks, thereby grounding future prediction in the robot's visible body and its action-induced motion.

IllustratedReading report

FlowPilot: Real-Time World-Action Modeling for Agile UAV Navigation

Wang, Runqing; Yu, Ding; Min, Pengyuan +6 authors

1 Aug 2026

We present FlowPilot, a compact world-action model for real-time onboard UAV navigation from depth. In closed-loop simulation, it outperforms learning- and optimization-based baselines under increasing clutter and commanded speeds up to 8m/s.

IllustratedReading report

Disentangling Visuo-Tactile Foresight: Oracle-Guided Interface Discovery for World Action Models

Yao, Zihang; Ding, Chaoyue; Yu, Yingying

WAMs Not applicable

1 Aug 2026

To make this interface independently studyable, we introduce Oracle Visuo-Tactile Foresight (OVTF), a controlled framework that supplies paired RGB and tactile futures from successful trajectories verified in simulation. Within OVTF, we propose Asymmetric Phase-Local Future Memory (AFM), in which visual memory reads future vision, each tactile memory jointly attends to its own tactile stream and phase-aligned future vision, and cross-tactile access is blocked.

IllustratedReading report

Diagnosing and Mitigating Perception-Decision Misalignment in Omni-LLMs via Modality Subspace Activation

Jiang, Hongbo; Li, Jie; Shen, Yunhang +2 authors

Not assigned Not applicable

31 Jul 2026

To rectify this, we propose Modality Subspace Activation (MSA), a training-free inference-time framework that uses Singular Value Decomposition (SVD) to estimate modal activation strengths.

IllustratedReading report

FBFM: A Training-Free Asynchronous Feedback Mechanism for Flow-Matching in World-Action Models Execution

Li, Peize; Zhang, Ruimeng; Zhang, Ru +3 authors

WAMs Outside quadrants

31 Jul 2026

To address this, we propose Feedback Flow Matching (FBFM), a training-free inference mechanism that pushes re-grounding inside the actively generated chunk.

IllustratedReading report

Paired Exact-Reset Evaluation of a Prediction-Derived Medium-to-Full World-Model Cascade

Pastor, Malo de

Evaluation metrics Not applicable

30 Jul 2026

Existing adaptive-inference and world-action-model systems use cheap-stage outputs or predicted futures to allocate additional computation. We study a narrower question: under paired exact-reset physical outcomes, can a Medium-derived interface predict when switching to a separately frozen Full predictor improves task-specific decision loss enough to justify sequential overhead?

IllustratedReading report

ST-WAM: Semantic-Temporal World Action Model for Robust Manipulation under Visual Distribution Shifts

Wang, Mingxin; Hu, Bin; Qian, Bin +12 authors

WAMs Outside quadrants

30 Jul 2026

Rather than correcting the predicted futures, we propose Semantic-Temporal WAM (ST-WAM) to improve action robustness by using DINOv3 as a shared semantic representation for future prediction and history retrieval while retaining fine-grained VAE dynamics. It achieves 98.7% on LIBERO and 92.8% on RoboTwin 2.0; more importantly, compared with Fast-WAM, it improves zero-shot LIBERO-Plus performance by 21.3 percentage points and more than doubles real-world success under visual shifts from 25.8% to 61.5%.

Paper Code Project

IllustratedReading report

QuantWAMs: Calibrating at the Right Granularity for World Action Models

Zhou, Jiacheng; Lv, Jinfan; Li, Ruixuan +4 authors

WAMs Outside quadrants

30 Jul 2026

We present QuantWAMs, a PTQ framework that aligns quantization decisions with the calibration context defined by model structure, rollout distribution, and task objective.

IllustratedReading report

EgoGenesis: Egocentric World-Action Modeling with Online Anchored Projective Memory and Action-3D RoPE

Yan, Zexuan; Wu, Yuzhou; Ma, Yue +9 authors

Benchmarks & simulators Not applicable

30 Jul 2026

We present \method, an egocentric world-action simulator that synthesizes controllable, high-quality manipulation videos to expand scarce real-world training data. \method{} builds on a pretrained video generation prior and introduces two geometry-aware conditioning mechanisms.

IllustratedReading report

LeapBot-WA: World-Anchor Action Models via Predictive Latent Alignments

Liu, Pei; Zheng, Nan; Zhang, Lang +8 authors

WAMs Outside quadrants

30 Jul 2026

In this paper, we propose LeapBot-WA, which establishes a novel Predictive-Latent paradigm for WAMs by operationalizing the Joint-Embedding Predictive Architecture (JEPA) as a World-Anchor. To bridge the modality gap between non-Gaussian predictive features and diffusion priors, we introduce the Isotropic Semantic Autoencoder (ISAE), which reshapes the anchor's latent space into a diffusion-friendly manifold to prevent off-manifold drift.

IllustratedReading report

DC-WAM: Dynamic-Centric Visual Supervision and Reasoning for World-Action Models

Ji, Haoyuan; Fan, Lingxiang; Su, Shang +4 authors

28 Jul 2026

We propose DC-WAM, a dynamic-centric WAM framework that redistributes supervision and computation in the RGB video branch.

IllustratedReading report

HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone

AI, Simple; :; Wei, Yuteng +16 authors

Datasets Not applicable

28 Jul 2026

We present HiFi-UMI, a portable UMI data-production system co-designed for trajectory accuracy, inter-gripper relative pose, synchronization, and field of view: head-mounted offline stereo-inertial SLAM, native rather than reconstructed relative pose, a shared microsecond GPIO trigger, and two wide-angle cameras per hand covering ~200 degrees.

IllustratedReading report

RoboHarness: Memory-Driven Orchestration of Heterogeneous Robot Policies for Long-Horizon Planning

Huang, Jinbang; Hu, Yuanzhao; Li, Zhiyuan +6 authors

Related resources Not applicable

28 Jul 2026

We propose RoboHarness, a unified framework that encapsulates independently developed robot control systems as reusable agentic skills.

IllustratedReading report

N₀-TWAM: Scaling Tactile-Native World-Action Model for Contact-Rich Manipulation

Team, NeoteAI; Team, Fudan TEAI

26 Jul 2026

We present N0N_0-TWAM, a tactile-native world-action model for contact-rich manipulation that predicts both future vision and future contact. To improve long-horizon and multi-stage manipulation, we introduce tactile contact events for task staging and advance through them during execution.

Paper Code Project

IllustratedReading report

GeoWorldAD: Geometry World Action Model for Autonomous Driving

Zhang, Songyan; Tian, Jinyuan; Li, Hanbing +9 authors

23 Jul 2026

In this work, we propose GeoWorldAD, a geometry world action model that grounds trajectory planning in ego-aligned 3D space and anticipates short-horizon scene evolution with latent future geometry tokens. Experiments on NAVSIM v1 and v2 demonstrate state-of-the-art performance, highlighting the effectiveness of explicit 3D geometry grounding and future geometry world modeling for safe and efficient autonomous driving.

IllustratedReading report

NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation

NVIDIA; Aarti Basant; Amlan Kar +31 authors

WAMs Not applicable

23 Jul 2026

To overcome these limitations, we introduce OmniDreams, a foundation generative world model mid- and post-trained from the Cosmos diffusion model to autoregressively generate action-conditioned videos in real time. We additionally show preliminary results indicating that a world-action model (WAM) post-trained from OmniDreams achieves strong performance on the Physical AI Autonomous Vehicles NuRec dataset, surpassing the VLA-based Alpamayo 1.5 research policy model while using only 1/5 the total parameters.

Paper Code Project

IllustratedReading report

PerceptDrive: Perception Prior World-Action Modeling with Adaptive Expert Routing for End-to-End Autonomous Driving

Liu, Yushan; Lv, Tianxiong; Wang, Bohua +11 authors

22 Jul 2026

Experiments show that PerceptDrive achieves state-of-the-art performance with 90.4 PDMS on NAVSIM v1 and 90.2 EPDMS on NAVSIM v2, outperforming existing methods.

IllustratedReading report

WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory

Su, Haisheng; Liu, Zongdai; Jin, Xin +13 authors

21 Jul 2026

In this paper, we introduce WorldScape Policy 2.0, a controllable WAM with reasoning-augmented long short-term memory.

Paper Code Project

IllustratedReading report

Test-Time Scaling for World Action Models via Zero-Shot Geometric Evaluation

Zhao, Zesen; Cho, Minkyoung; shen, Hui +4 authors

WAMs Outside quadrants

19 Jul 2026

We propose \methodgated, a training-free selective test-time scaling framework for WAMs.

IllustratedReading report

GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch

GigaWorld Team; Angen Ye; Angyuan Ma +26 authors

WAMs Outside quadrants

17 Jul 2026

Building upon this framework, we present GigaWorld-Policy-0.5, an enhanced action-centered WAM designed for more efficient robot control.

Paper Code Project

IllustratedReading report

BadWAM: When World-Action Models Dream Right but Act Wrong

Li, Qi; Yang, Xingyi; Wang, Xinchao

Related resources Not applicable

16 Jul 2026

We introduce BadWAM, a unified framework for modeling and evaluating World-Action Drift Attacks: a new class of WAM-specific adversarial attacks that use small visual perturbations to break the alignment between what a WAM imagines and what it executes.

Paper Code Project

IllustratedReading report

AeroAct: Action-Centered World-Action Models for Language-Conditioned Quadrotor Flight

Zhang, Xinhong; Zhu, Qiyuan; Huang, Yubo +8 authors

16 Jul 2026

We present AeroAct, an action-centered world-action model (WAM) for quadrotor navigation. To obtain aligned visual, state, language, and dynamically feasible action data, we build a DiffAero-based pipeline with complementary Isaac Lab and 3D Gaussian splatting renderers.

IllustratedReading report

Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control

Hong, Jihoon; Skifstad, Julian; Dai, Qiyue +2 authors

WAMs Outside quadrants

16 Jul 2026

World Action Models (WAMs) enable semantically- and physically-informed control but are brittle under distribution shift. In this work, we use mechanistic interpretability to study how robustness-relevant perturbations are represented in WAM activation space.

Paper Code Project

IllustratedReading report

FlowWAM: Optical Flow as a Unified Action Representation for World Action Models

Chen, Yixiang; Li, Peiyan; Xu, Yuan +13 authors

14 Jul 2026

On WorldArena world modeling, it achieves the best overall EWMScore (63.71) with an 18.4% relative improvement in trajectory accuracy.

Paper Code Project

IllustratedReading report

From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence

Liang, Yuanzhi; Zhan, Xufeng; Huang, Haibin +2 authors

Related resources Not applicable

13 Jul 2026

Building on this analysis, we propose a co-evolution roadmap for physical intelligence centered on the \emph{embodied brain}, a long-term model target for integrating multimodal context, comparing candidate interventions, and issuing state-transition or capability requests rather than direct actuator commands.

IllustratedReading report

Towards Predictive, Aligned, and Scalable Robot Learning

Tang, Peijun; Xie, Shangjin; Huang, Baifu +6 authors

13 Jul 2026

We introduce Lumo-2, a latent world-action model that generates actions by reasoning over world dynamics in latent space. Central to our approach is the hypothesis that action generation quality is governed by the geometry of the latent space.

IllustratedReading report

Artificial Foveated Perception for Mitigating Shortcut Learning in Robotic Foundation Models

Sun, Xiatao; Zhuang, Yuan; Negrete, Mateo Sanchez Lopez +9 authors

VLA Not applicable

12 Jul 2026

We propose Artificial Foveated Perception (AFP), a lightweight, policy-agnostic module that takes the same vision and language inputs as Vision-Language-Action and World Action Model pipelines and predicts task-conditioned masks over relevant objects, the robot, and other action-critical regions. We evaluate AFP across state-of-the-art robotic foundation models and show that foveated perception reduces fine-tuning time, suppresses overfitting, and improves generalization under environmental perturbations.

IllustratedReading report

DIM-WAM: World-Action Modeling with Diverse Historical Event Memory

Wang, Kai; Gu, Zhaopeng; Chen, Yixiang +7 authors

12 Jul 2026

To address long-term forgetting and poor awareness of the global task state, we introduce DiM-WAM, a memory-augmented world-action model that integrates multi-scale historical context, local future dynamics, and global task progress.

IllustratedReading report

FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space

Murray, Michael; Chen, Daphne; Bagaria, Simran +7 authors

WAMs Not applicable

9 Jul 2026

We present FlowDAgger, a sample- and compute-efficient method for adapting frozen generative robot policies from human interventions in latent space. FlowDAgger outperforms supervised fine-tuning and latent-space RL baselines and preserves pretrained skills on held-out tasks, offering a practical path for adapting robot foundation models in the real world.

Paper Code Project

IllustratedReading report

Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents

Yixian Zhang; Huanming Zhang; Feng Gao +13 authors

VLA Not applicable

9 Jul 2026

Contribution summary not yet recorded.

IllustratedReading report

Understanding and Mitigating the Video-Action Generalization Gap via Temporal Ratio

Mishra, Utkarsh A.; Chen, Yongxin; Xu, Danfei +3 authors

WAMs Outside quadrants

9 Jul 2026

To explain this behavior, we introduce the Temporal Ratio (TR), an attention-based measure of how strongly the action head relies on future latent rollouts relative to the anchored current frame. Finally, based on these findings, we propose an inference-time adaptive guidance method, which exploits this intrinsic feature attention pattern to dynamically amplify compositional video conditioning signals precisely when the policy relies on future rollouts.

IllustratedReading report

WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time

Feng, Yusen; Han, Bingchen; Lyu, Jiangran +13 authors

WAMs Pending verification

9 Jul 2026

We present WAM-TTT, a test-time training framework for steering world action models from raw human videos. To make this memory useful for control, we introduce a meta-training stage that aligns human demonstrations with robot behaviors using paired human-robot data and a key--value memory reconstruction objective.

IllustratedReading report

EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data

Li, Baoyu; Yin, Xinchen; Lin, Mengying +2 authors

8 Jul 2026

We introduce EgoWAM, a controlled human-robot co-training framework that fixes the policy backbone, action head, and data mixture while varying only the world prediction target, comparing Pixel, DINO, and 3D motion flow.

IllustratedReading report

WAM4D: Fast 4D World Action Model via Spatial Register Tokens

Li, Ying; Wei, Xiaobao; Cao, Jiajun +10 authors

WAMs Outside quadrants

7 Jul 2026

To address the trade-off, we present WAM4D, a fast 4D world action model that uses lightweight spatial register tokens as training-time future-depth readouts to transfer pretrained geometric priors into a causal video-action transformer, then removes the register branch for lightweight action inference. Comprehensive experiments on RoboTwin 2.0 and challenging real-world manipulation tasks show that WAM4D improves spatial consistency and achieves competitive action prediction while maintaining efficient inference.

IllustratedReading report

Learning 4D Geometric Priors for Inference-Efficient World Action Models

Zhang, Jianjun; Zhu, Jian; Su, Taiyi +4 authors

WAMs Outside quadrants

6 Jul 2026

We propose MECo-WAM, a Multi-Expert Co-Training World Action Model that injects action-relevant 4D geometric priors into video-action representations while preserving the original lightweight inference graph. To transfer geometric knowledge into the deployed video-action pathway, we introduce decayed 4D read-mask attention, which provides restricted current-frame geometric guidance early in training and progressively removes this dependency.

IllustratedReading report

UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation

Liu, Mengmeng; Zhang, Diankun; Liu, Jiuming +7 authors

WAMs Outside quadrants

6 Jul 2026

We propose UNIVERSE, a unified video-action model built upon a single mask-modulated Diffusion Transformer. To ensure causal validity and efficient deployment, we introduce a Modality-Decoupling Visibility Mask, which shares historical context across modalities while blocking mutual attention between future video and trajectory tokens.

IllustratedReading report

DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulation

Zhu, Jian; Zhang, Jianjun; Su, Taiyi +10 authors

WAMs Outside quadrants

6 Jul 2026

To address both the decomposition gap and the need for a controlled WAM-VLA comparison, we introduce DSWAM, a Dual-System World Action Foundation Model for fine-grained robot manipulation. To provide a fair real-robot comparison with VLA policies, we build and evaluate DSWAM under the DeMaVLA real-world deformable manipulation setting with matched robot platform, pretraining data, post-training data, and evaluation criteria.

IllustratedReading report

ABot-M0.5: Unified Mobility-and-Manipulation World Action Model

Chen, Ronghan; Yang, Yandan; Tang, Zuojin +18 authors

6 Jul 2026

We propose ABot-M0.5, a new WAM built on the insight that mobile manipulation requires alignment at three levels: temporal granularity, action space, and train-test consistency. To align temporal granularity, we introduce intermediate latent actions that capture local visual state transitions and serve as an bridging action space between video latents and embodiment-specific controls.

Paper Code Project

IllustratedReading report

RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies

Tianxing Chen; Yue Chen; Zixuan Li +41 authors

Benchmarks & simulators Not applicable

5 Jul 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models

Ye, Angen; Ke, Weijie; Wang, Xiaofeng +7 authors

WAMs Outside quadrants

5 Jul 2026

We propose HALO-WA, a hybrid-attention latent-guided online reinforcement learning (RL) framework for WA models, which leverages latent features and action priors from the WA generation process through a lightweight actor-critic adapter to enable fast online adaptation to real deployment errors.

IllustratedReading report

Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI

Team, Kairos; Wang, Fei; You, Shan +21 authors

3 Jul 2026

We introduce \textbf{Kairos}, a regret-aware native world-action model stack for Physical AI. Experiments on embodied world-model benchmarks, world-action benchmarks, long-horizon generation, and inference-efficiency evaluation show that Kairos achieves superior performance while offering a favorable efficiency to capability trade-off.

Paper Code Project

IllustratedReading report

VT-WAM: Visual-Tactile World Action Model for Contact-Rich Manipulation

Tian, Shuai; Zheng, Yupeng; Zheng, Yuhang +7 authors

2 Jul 2026

In this paper, we introduce VT-WAM, a Visual-Tactile World Action Model that jointly learns future visual prediction, tactile deformation prediction, and action prediction within a unified flow matching framework. Across six real-world contact-rich manipulation tasks, VT-WAM achieves a 71.67% average success rate, outperforming Fast-WAM by 26.67% and OmniVTLA by 35.84%.

IllustratedReading report

Bridge-WA: Predicting Where and How the World Changes for Robotic Action

Bai, Yongjie; Wang, Hanting; Dai, Mingtong +3 authors

2 Jul 2026

We present Bridge-WA, a lightweight world-action framework that distills a frozen future-change teacher into three compact priors: future tokens for intended outcomes, change maps for intervention support, and motion-flow maps for local transition direction.

Paper Code Project

IllustratedReading report

Efficient Sim-to-Real Transfer of World-Action Models from Synthetic Priors

Wang, Zixing; Sivakumar, Kausik; Shang, Jinghuan +5 authors

29 Jun 2026

To this end, we build upon Cosmos Policy, a video diffusion model adapted for visuomotor control. We evaluate our approach across object lifting, drawer opening, and pick-and-place tasks using ∼800{\sim}800 synthetic demonstrations per task and no real demonstrations.

IllustratedReading report

FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation

Zhang, Lingfeng; Gong, Zeying; Hao, Xiaoshuai +7 authors

WAMs Outside quadrants

29 Jun 2026

We introduce FutureNav, a VLM-based unified world-action modeling framework for vision-and-language navigation. Extensive experiments show that, with only a 4B-scale backbone, FutureNav achieves state-of-the-art performance on multiple VLN benchmarks and substantially outperforms prior VLN methods, paving the way toward future world-action models for VLN.

Paper Code Project

IllustratedReading report

Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation

Chen, Hong; Liu, Daqi; Zhang, Zehan +10 authors

29 Jun 2026

To address these issues, we propose SWAM (Spatial-perceiving World Action Model), a task-centric joint observation-action generation framework. Extensive experiments show that SWAM significantly outperforms state-of-the-art two-stage planners in success rate, trajectory accuracy, and inference efficiency, while demonstrating robust zero-shot generalization to unseen environments.

IllustratedReading report

World Action Models Enable Continual Imitation Learning with Recurrent Generative Replays

Govind, Manish Kumar; Reilly, Dominick; Patel, Smit +2 authors

25 Jun 2026

We build on this generative capability to propose Recurrent Generative Replay (REGEN), a continual imitation learning framework that synthesizes pseudo-replay trajectories, enabling a robot policy to rehearse previously learned tasks without storing their original human demonstrations.

Paper Code Project

IllustratedReading report

PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation

Yuhang Huang; Xuan Lv; Junyan Xu +25 authors

Benchmarks & simulators Not applicable

23 Jun 2026

To address this, we present PAIWorld, a framework that augments diffusion-transformer world models via three core components: (1) Geometry-Aware Cross-View Attention blocks that establish an explicit pathway across views, (2) Geometric Rotary Position Embedding that encodes camera ray directions and extrinsic poses into the attention mechanism, and (3) Latent 3D-REPA, which distills 3D-aware features from frozen 3D foundation models to ensure 3D consistency. Built upon a DiT-based world foundation model, PAIWorld achieves state-of-the-art multi-view 3D consistency on robotic manipulation benchmarks, ranking 1st on the WorldArena leaderboard and 2nd on the AgiBot-Challenge2026 leaderboard, wh…

IllustratedReading report

Cosmos 3: Omnimodal World Models for Physical AI

NVIDIA; Aditi; Niket Agarwal +292 authors

23 Jun 2026

We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture. Our evaluation demonstrates that Cosmos 3 establishes a new state-of-the-art across a diverse suite of understanding and generation tasks, demonstrating omnimodal world models as scalable, general-purpose backbones for embodied agents.

Paper Code Project

IllustratedReading report

Critique of Agent Model

Eric Xing; Mingkai Deng; Jinyu Hou

Related resources Not applicable

22 Jun 2026

Contribution summary not yet recorded.

IllustratedReading report

dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models

Wu, Yuhao; Liu, Yitian; Shen, Weijie +13 authors

VLA Not applicable

22 Jun 2026

To solve this problem, we propose \textbf{dVLA-RL}, shifting the learning objective from the marginal action probability to the joint probability of the sampled generation path. Leveraging this intrinsic fexibility, we introduce a unified step scheduling approach for complex multi-task learning, tailoring denoising steps to specific task complexities to maximize both success rates and computational effciency.

IllustratedReading report

A Watermark for Vision-Language-Action and World Action Models

Liu, Yule; Liu, Shuai; Wei, Jiaheng +1 authors

Related resources Not applicable

22 Jun 2026

To address this, we propose the \emph{keyed latent-provenance verification} method, which fingerprints the policy through the seed of the Gaussian noise vector that the models draw before generation.

IllustratedReading report

Attacking the Trusted Imagination: Oracle-Level Integrity Attacks on Imagine-then-Act World Models

Chen, Linghan; Ji, Kaiyan; Guo, Minyu

Related resources Not applicable

22 Jun 2026

Many recent vision-language-action (VLA) policies adopt an imagine-then-act design. A world-action model (WAM) first imagines a short future as a latent trajectory z~, on which the action is then conditioned.

IllustratedReading report

Geometric Action Model for Robot Policy Learning

Han, Jisang; Jeon, Seonghu; Jung, Jaewoo +7 authors

22 Jun 2026

We propose the Geometric Action Model (GAM), a language-conditioned manipulation policy that directly repurposes a pretrained geometric foundation model (GFM) as a shared substrate for perception, temporal prediction, and action decoding.

Paper Code Project

IllustratedReading report

MV-WAM: Manifold-Aware World Action Model with Value Augmentation

Chen, Jintao; Jia, Peidong; Wuwu, Qingpo +13 authors

19 Jun 2026

Recent world action models achieve strong in-domain performance, yet their gains do not extend proportionally to out-of-distribution scenarios. To address this, we propose MV-WAM, a novel end-to-end framework that jointly models visual prediction, action generation, and value estimation designed to effectively leverage video priors during both training and inference for enhanced action generalization.

IllustratedReading report

World Action Models: A Survey

Shen, Qiuhong; Zhang, Shihua; Liao, Yue +5 authors

Related resources Not applicable

18 Jun 2026

World Action Models (WAMs) are embodied predictive-action models that make a forecast of the future available to action. Recent WAMs repurpose large video generation models, and a parallel line relies on language or vision-language backbones without a video-generation core.

Paper Code Project

IllustratedReading report

MemoryWAM: Efficient World Action Modeling with Persistent Memory

Yang, Sizhe; Mu, Juncheng; Wei, Tianming +8 authors

WAMs Outside quadrants

18 Jun 2026

To address this challenge, we introduce MemoryWAM, a world action model with efficient persistent memory. Across long-horizon, memory-dependent manipulation tasks in both simulation and the real world, MemoryWAM outperforms strong vision-language-action (VLA) and WAM baselines while maintaining favorable computational efficiency.

IllustratedReading report

EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies

Ganlin Yang; Zhangzheng Tu; Yuqiang Yang +10 authors

VLA Not applicable

18 Jun 2026

Contribution summary not yet recorded.

IllustratedReading report

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

Zhang, Yuyang; Zhang, Wenyao; Qi, Zekun +7 authors

17 Jun 2026

We propose ImageWAM, a simple WAM framework that repurposes pretrained image editing models for robot action prediction. ImageWAM outperforms standard VLA baselines and matching competitive WAMs without additional policy pretraining across different simulator and real-world experiments.

Paper Code Project

IllustratedReading report

WAM-RL: World-Action Model Reinforcement Learning with Reconstruction Rewards and Online Video SFT

Qian, Zezhong; Chi, Xiaowei; Qi, Yu +3 authors

16 Jun 2026

To address these limitations, we propose WAM-RL, a reinforcement learning framework that enables joint optimization of the world model and the action model through online interaction with the environment. By allowing the two components to co-evolve, our approach enhances fine-grained control and adaptability.

IllustratedReading report

Metis: A Generalizable and Efficient World-Action Model for Autonomous Driving and Urban Navigation

Li, Jingyu; Liu, Zhe; Hu, Dongnan +10 authors

WAMs Outside quadrants

14 Jun 2026

To address both issues, we propose Metis, an end-to-end WAM framework that decouples video generation and action prediction. To enhance efficiency, we introduce an asymmetric attention mask that enables joint training of both experts while allowing the action model to bypass explicit video generation during inference.

IllustratedReading report

LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies

Chen, Jialei; Wang, Kai; Chen, Kang +9 authors

14 Jun 2026

We present LaWAM, a Latent World Action Model that exposes predictive dynamics to robot policies through compact latent visual subgoals instead of reconstructed future video. LaWAM achieves state-of-the-art or competitive success rates (SRs) across LIBERO (98.6% SR), RoboTwin (91.22% SR), and real-world manipulation tasks while retaining low-latency inference.

Paper Code Project

IllustratedReading report

Retrieve, Don't Retrain: Extending Vision Language Action Models to New Tasks at Test Time

Park, Jeongeun; Park, Juhan; Kim, Taekyung +3 authors

14 Jun 2026

On PushT, we study how retrieval provides a reusable high-level motion prior for cross-embodiment generalization to unseen goal angles, while on RoboTwin 2.0 our method outperforms cross-embodiment baselines on unseen tasks, and we additionally demonstrate the method on a real robot.

Paper Code Project

IllustratedReading report

MemoryVAM: Integrating Memory into Video Action Model for Robot Manipulation

Yuxin Jiang; Chang Yu; Yunuo Chen +4 authors

13 Jun 2026

Contribution summary not yet recorded.

IllustratedReading report

RepWAM: World Action Modeling with Representation Visual-Action Tokenizers

Wang, Junke; Zhang, Qihang; Yang, Shuai +5 authors

13 Jun 2026

This work presents RepWAM, a representation-centric world action model (WAM) built on representation visual-action tokenizers.

IllustratedReading report

WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation

Yang, Ning; Huang, Yan; Peng, Kaiwen +9 authors

13 Jun 2026

To address these limitations, we propose WAM-Nav, a Latent World-Action Model for embodied visual navigation that jointly learns action generation and latent visual foresight, enabling more robust and foresighted navigation decisions without compromising inference efficiency. To further encourage smooth and consistent trajectory generation, we introduce a dual-stream contextual conditioning mechanism that integrates episode-level ego-motion history with sequential visual observations.

IllustratedReading report

MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models

Yu, Hanyang; Lin, Haitao; Zhang, Jingbo +4 authors

11 Jun 2026

To overcome these limitations, we introduce MaskWAM, an object-centric world-action model. Evaluations on LIBERO, RoboTwin, and real-world tasks demonstrate that MaskWAM significantly outperforms baselines in both language-clear and language-ambiguous tasks.

IllustratedReading report

NavWAM: A Navigation World Action Model for Goal-Conditioned Visual Navigation

Azuma, Daichi; Miyanishi, Taiki; Sakamoto, Koya +6 authors

11 Jun 2026

We propose Navigation World Action Model (NavWAM), a diffusion-transformer policy that turns navigation world-model prediction into executable action by representing future observations, goal-progress values, and action chunks in a shared latent sequence. We build NavWAM through simulation pretraining and real-robot adaptation, and evaluate it on image-goal navigation against planning-based world models and a representative direct navigation policy.

IllustratedReading report

Diffusion Transformer World-Action Model for AV Scene Prediction

Sharifullin, Ruslan; Jiang, Benjamin; Chew, Kai Xi

Benchmarks & simulators Not applicable

11 Jun 2026

Action-conditioned world models let an autonomous vehicle predict future camera scenes from its own planned controls, enabling planning and simulation without real-world rollouts, but at compact, trainable scale the futures are ambiguous and the field's standard distortion metrics actively mislead: they reward a blurry regression mean over a realistic prediction. We confront this with a compact latent world model that, given the present front-camera latent and a sequence of ego-actions, predicts future scene latents a frozen decoder renders to 256×256256 \times 256 frames up to 8 seconds ahead, evaluated on 150 held-out nuScenes scenes.

IllustratedReading report

FAWAM: Force-Aware World Action Models for Closed-Loop Contact-Rich Manipulation

He, Haotian; Yan, Zeyu; Liu, Qipeng +2 authors

11 Jun 2026

In this paper, we propose FAWAM, a force-aware world action model that incorporates force information at three levels: perception, prediction, and closed-loop execution.

Paper Code Project

IllustratedReading report

EWAM: An Enhanced World Action Model for Closed-Loop Online Adaptation in Embodied Intelligence

Zhou, Xin; Miao, Cong

WAMs Outside quadrants

10 Jun 2026

In this paper, we propose the Enhanced World Action Model (EWAM), a closed-loop online adaptation architecture built upon a pretrained and fully frozen Cosmos3 backbone network.

IllustratedReading report

World Pilot: Steering Vision-Language-Action Models with World-Action Priors

Lin, Zefu; Cui, Rongxu; Xu, Junjia +4 authors

10 Jun 2026

We present World Pilot, a VLA framework that augments the policy with priors from a World-Action Model (WAM), routed into the decision chain through two complementary pathways. World Pilot attains a state-of-the-art Total success rate of 84.7% on the LIBERO-Plus zero-shot OOD benchmark and the highest success rate on every real-robot setting across four manipulation tasks, with the largest margins under shifts in viewpoint, geometry, deformable state, and pose.

Paper Code Project

IllustratedReading report

Making Foresight Actionable: Repurposing Representation Alignment in World Action Models

Qiu, Lu; Li, Yizhuo; Chen, Yi +3 authors

10 Jun 2026

In this paper, we propose AGRA, an Action-Grounded Representation Alignment objective that regularizes the world-action interface by aligning intermediate video diffusion features with spatially coherent semantic representations from a foundation visual encoder.

IllustratedReading report

Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination

Li, Jiajun; Guo, Tiecheng; Ye, Yifan +9 authors

10 Jun 2026

We introduce Efficient-WAM, a World-Action Model that reduces the cost of future imagination while preserving its control benefit.

Paper Code Project

IllustratedReading report

Next Forcing: Causal World Modeling with Multi-Chunk Prediction

Xu, Gangwei; Zhang, Qihang; Zhou, Jiaming +4 authors

9 Jun 2026

In this paper, we present Next Forcing, a multi-chunk prediction (MCP) framework for causal world modeling that enables faster training, higher accuracy, and accelerated inference. During training, the MCP modules significantly accelerate convergence and improve converged accuracy, especially at high frame rates: at 50 fps, Next Forcing achieves a 93.1% relative improvement over LingBot-VA at 5k training steps and 2.3x faster convergence, and establishes new state-of-the-art results on the RoboTwin benchmark (94.1/93.5% on Clean/Random).

Paper Code Project

IllustratedReading report

HiMem-WAM: Hierarchical Memory-Gated World Action Models for Robotic Manipulation

Sun, Xiaoquan; Zhang, Ruijian; Cao, Chen +12 authors

VLA Not applicable

8 Jun 2026

To address this, we present HiMem-WAM, a Hierarchical Memory-Gated WAM that integrates motion-centric latent actions, high-level skill latents, and boundary-triggered memory updates. Specifically, we develop a hierarchical latent action framework that jointly learns low-level motion and high-level skill latents, providing structured temporal abstraction.

IllustratedReading report

AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing

Cai, Jisong; Ling, Long; Chu, Shiwei +10 authors

8 Jun 2026

Therefore, we propose AHA-WAM, an Asynchronous Horizon-Adaptive World-Action Model built on a dual Diffusion Transformer (DiT) architecture that reorganizes world-action modeling around this temporal asymmetry. To support asynchronous execution, we introduce horizon-adaptive offset training and Observation-Guided Video-Context Routing (OVCR), which together let the action expert exploit long-horizon world context while remaining responsive to real-time execution state without rerunning the video DiT.

Paper Code Project

IllustratedReading report

MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation

Zheng, Jia; Ma, Teli; Fan, Yudong +3 authors

8 Jun 2026

We present MotionWAM, a real-time WAM that drives autonomous humanoid loco-manipulation from a single egocentric camera by conditioning the policy on the intermediate denoising features of a video world model. On nine real-world Unitree G1 tasks, MotionWAM runs in real time, substantially outperforms Vision-Language-Action (VLA) baselines fine-tuned on the same demonstrations by over 30% in overall success rate, and executes task-driven foot interaction that decoupled upper-lower policies cannot reach.

IllustratedReading report

C3^3ache: Accelerating World Action Models with Cross Inference Chunk Cache

Zhao, Weisen; Nguyen, Lam; Lu, Zhicong +1 authors

WAMs Outside quadrants

7 Jun 2026

We introduce C3^3ache, a training-free method that caches and reuses these residuals across inference chunks at the same denoising step. Experiments on benchmarks with a Fast-WAM backbone show that C3^3ache achieves up to a 2.5×2.5\times speedup in total wall-clock inference time, with negligible degradation in task success rate.

IllustratedReading report

Dream-Tac: A Unified Tactile World Action Model for Contact-Rich Robot Manipulation

Lou, Yunfan; Ye, Yifan; Fu, Yankai +7 authors

7 Jun 2026

In this paper, we propose Dream-Tac, a unified Tactile-World Action Model that jointly models actions, future visual observations, and tactile dynamics.

IllustratedReading report

ImagineUAV: Aerial Vision-Language Navigation via World-Action Modeling and Kinodynamic Planning

Liu, Xuchen; Huang, Jiawei; Xia, Shihao +3 authors

7 Jun 2026

To address this, we propose ImagineUAV, an imagination-driven framework leveraging cascaded world-action modeling. With only 1.3B parameters, ImagineUAV outperforms prior VLN and VLA baselines on benchmarks and real-world flights, validating the practicality of imagination-driven aerial navigation.

IllustratedReading report

SIMPLE: Simulation-Based Policy Learning and Evaluation for Humanoid Loco-manipulation

Wei, Songlin; Ni, Zhenhao; Liu, Jie +9 authors

Benchmarks & simulators Not applicable

6 Jun 2026

To this end, we present SIMPLE, a unified simulation testbed for humanoid policy learning and evaluation.

Paper Code Project

IllustratedReading report

Light-WAM: Efficient World Action Models with State-Fusion Action Decoding

Li, Ziang; Cheng, Dongzhou; Wang, Yibin +5 authors

WAMs Outside quadrants

6 Jun 2026

We propose Light-WAM, a lightweight World Action Model for efficient robot manipulation. Experiments demonstrate that Light-WAM maintains strong performance on LIBERO and achieves usable multi-task performance on RoboTwin 2.0, while using only 0.44B trainable parameters.

IllustratedReading report

Dreaming when Necessary: Advancing World Action Models with Adaptive Multi-Modal Reasoning

Tang, Yinzhou; Xu, Jingbo; Shang, Yu +4 authors

5 Jun 2026

Motivated by this observation, we propose \textbf{AdaWAM}, a world action model with adaptive multimodal reasoning abilities. Experiments on both simulated and real-world embodied tasks show that AdaWAM substantially improves inference efficiency while outperforming state-of-the-art embodied policies.

IllustratedReading report

World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis

Yang, Yi; Liu, Zhihong; Kou, Siqi +9 authors

WAMs Outside quadrants

4 Jun 2026

We propose world-language-action (WLA) models as a new class of embodied foundation models. Our WLA-0 prototype, with 2B active parameters, achieves 40 ms per inference on an NVIDIA RTX 5090.

IllustratedReading report

Flash-WAM: Modality-Aware Distillation for World Action Models

Akbari, Arman; Zhang, Ci; Akbari, Arash +6 authors

3 Jun 2026

We introduce \textbf{Flash-WAM}, a modality-aware step-distillation framework inspired by consistency distillation that selects the consistency function for each modality to match its noise regime: a linear-gradient-scaling parametrization for the action stream's low-noise regime, paired with a variance-preserving parametrization for the video stream's high-noise regime, grounded in a structural analysis of the consistency-function family that characterizes the achievable gradient scaling under the consistency boundary condition.

Paper Code Project

IllustratedReading report

Unified Video-Action Joint Denoising for Dexterous Action and Data Generation

Wang, Dingrui; Wang, YuAn; Liu, Jinkun +4 authors

2 Jun 2026

We propose Donk, a unified video-action denoising model for dexterous hands.

IllustratedReading report

GeoSem-WAM: Geometry- and Semantic-Aware World Action Models

Ma, Fulong; Peng, Daojie; Yue, Wenjun +4 authors

WAMs Outside quadrants

2 Jun 2026

To address this, we propose a structured world modeling framework that enhances latent representations through geometric and semantic supervision. Alongside future RGB prediction, our model introduces two auxiliary prediction branches for future geometry and semantic representations, enabling it to jointly capture scene dynamics, spatial geometry, and semantic context within a unified latent space.

IllustratedReading report

WALL-WM: Carving World Action Modeling at the Event Joints

Shalfun Li; Victor Yao; Charles Yang +28 authors

1 Jun 2026

Experiments show that WALL-WM generalizes broadly across language, scenes, and tasks, achieving state-of-the-art performance in large-scale real-world generalization evaluation.

IllustratedReading report

AttenA+: Rectifying Action Inequality in Robotic Foundation Models

Peng, Daojie; Ma, Fulong; Cao, Jiahang +7 authors

VLA Not applicable

1 Jun 2026

To rectify this, we introduce AttenA+, an architecture-agnostic framework that prioritizes kinematically critical segments via velocity-driven action attention. Extensive experiments demonstrate that AttenA+ significantly elevates the ceilings of current state-of-the-art models.

IllustratedReading report

Beyond Task Success: Behavioral and Representational Diagnostics for WAM and VLA

Mai, Hung; Zhu, Bin; Do, Tuan

Evaluation metrics Not applicable

31 May 2026

We introduce a model-agnostic diagnostic framework that compares WAMs and VLAs through two complementary lenses: behavioral rollout analysis and sparse-autoencoder-based feature analysis.

IllustratedReading report

DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving

Shi, Chen; Xu, Jinrui; Shi, Shaoshuai +3 authors

27 May 2026

We present DriveWAM, a driving world-action model that adapts a pretrained video diffusion transformer into an autoregressive video-action policy. To incorporate high-level scene understanding, we introduce scene-evolving driving guidance, where a frozen VLM produces chunk-specific semantic intent to guide video-action generation.

Paper Code Project

IllustratedReading report

OASIS: Observation-Action Space Alignment via SE(3) Trajectory Prediction for Robotic Manipulation

Chen, Xinzhe; Ren, Sihua; Huang, Liqi +5 authors

VLA Not applicable

25 May 2026

We propose OASIS, a visuomotor policy that aligns the intermediate representation with the action space via SE(3)SE(3) end-effector trajectory prediction. Across simulation and real-world experiments, OASIS outperforms VLA and WAM baselines in success rate and out-of-distribution generalization.

IllustratedReading report

Point Tracking Improves World Action Models

Guan, Jiarui; Zhao, Wenshuai; Pei, Yue +3 authors

22 May 2026

We propose JOPAT, a JOint Pixel-And-Track World-Action Model that predicts latent visual observations, 2D point tracks with visibility, and actions in a single denoising diffusion transformer.

IllustratedReading report

Key-Gram: Extensible World Knowledge for Embodied Manipulation

Fan, Jingjing; Li, Siyuan; Ren, Botao +1 authors

VLA Not applicable

18 May 2026

In this paper, we introduce Key-Gram, a conditional-memory framework that separates language-derived world knowledge from visual-state reasoning for embodied control.

IllustratedReading report

How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning

Kim, Bosung; Wang, Ruiyi; Acuna, David +5 authors

Datasets Not applicable

16 May 2026

We introduce DeMiAn (Dense Multi-aspect Annotation), a two-stage approach that first re-labels demonstration segments with VLM-generated annotations along four complementary aspects: physical motion, scene composition, arm pose, and reasoning.

IllustratedReading report

WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation

Zhao, Baining; Xu, Jiacheng; Feng, Weicheng +13 authors

15 May 2026

To this end, we propose WorldVLN, the first autoregressive world action model for aerial VLN. On public outdoor and indoor benchmarks, WorldVLN consistently outperforms existing Vision-Language-Action baselines with 12\%+ success-rate gains and larger advantages on challenging cases.

Paper Code Project

IllustratedReading report

World Action Models: The Next Frontier in Embodied AI

Wang, Siyin; Shi, Junhao; Fu, Zhaoyang +11 authors

Related resources Not applicable

12 May 2026

Vision-Language-Action (VLA) models have achieved strong semantic generalization for embodied policy learning, yet they learn reactive observation-to-action mappings without explicitly modeling how the physical world evolves under intervention. A growing body of work addresses this limitation by integrating world models, predictive models of environment dynamics, into the action generation pipeline.

Paper Code Project

IllustratedReading report

The DAWN of World-Action Interactive Models

Lu, Hongbo; Yao, Liang; He, Chenghao +6 authors

12 May 2026

Experiments show that DAWN achieves strong planning performance and favorable safety-related results across multiple autonomous driving benchmarks.

Paper Code Project

IllustratedReading report

HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models

Feng, Qiuxuan; Yu, Jiale; Liu, Jiaming +8 authors

11 May 2026

Motivated by these findings, we propose HarmoWAM, an end-to-end WAM that fully leverages a world model to unify predictive and reactive control, enabling both generalizable transit and precise manipulation. Notably, HarmoWAM achieves strong zero-shot generalization across these scenarios, significantly outperforming prior state-of-the-art VLA models and WAMs by margins of 33% and 29%, respectively.

IllustratedReading report

When to Trust Imagination: Adaptive Action Execution for World Action Models

Wang, Rui; Zhang, Yue; Lin, Jiehong +4 authors

WAMs Outside quadrants

9 May 2026

In this work, we formulate adaptive WAM execution as a future-reality verification problem: the robot should execute longer when the WAM-predicted future remains reliable, and replan earlier when reality deviates from imagination. To this end, we propose Future Forward Dynamics Causal Attention (FFDC), a lightweight verifier that jointly reasons over predicted future actions, predicted visual dynamics, real observations, and language instructions to estimate whether the remaining action rollout can still be trusted.

IllustratedReading report

Geometry Guided Self-Consistency for Physical AI

Dai, Yinwei; Chen, Zhuofu; Yang, Lijie +1 authors

VLA Not applicable

8 May 2026

State-of-the-art physical AI models generate a chunk of actions per inference through diffusion or flow matching, iteratively refining an initial noise sample into an action trajectory. We introduce KeyStone, an inference-time self-consistency method for diffusion-based action generation that draws KK candidate action chunks in parallel from a shared model context, clusters them in continuous action space, and returns the medoid of the largest cluster -- no additional model required.

IllustratedReading report

NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Models

Huang, Wen; Sun, Haoran; Guo, Yongjian +8 authors

8 May 2026

We propose \textbf{NoiseGate}, which combines independent per-latent timestep sampling during backbone training, a lightweight Gating Policy Network that emits per-latent time increments during denoising, and task-reward optimization that trains the schedule policy without hand-crafted shape priors.

IllustratedReading report

Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Models

Ruan, Bo-Kai; Hsiao, Teng-Fang; Lo, Ling +1 authors

Evaluation metrics Not applicable

8 May 2026

Building on these findings, we introduce a value-free consensus strategy for test-time selection, which ranks candidate rollouts by agreement among predicted futures.

IllustratedReading report

Learning Visual Feature-Based World Models via Residual Latent Action

Zhang, Xinyu; Xu, Zhengtong; Tao, Yutian +3 authors

WAMs Outside quadrants

7 May 2026

Building on RLA, we propose *RLA World Model* (RLA-WM), which predicts RLA values via flow matching. RLA-WM outperforms both state-of-the-art feature-based and video-diffusion world models on simulation and real-world datasets, while being orders of magnitude faster than video diffusion.

Paper Code Project

IllustratedReading report

OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation

Liu, Yushan; Sun, Peibo; Li, Shoujie +7 authors

7 May 2026

We propose OA-WAM, an Object-Addressable World Action Model for robust robot manipulation. OA-WAM matches strong VLA and WAM baselines on LIBERO (97.8%) and SimplerEnv (79.3%), reaches state-of-the-art performance on the most relevant LIBERO-Plus geometric axes, and remains competitive on the seven-axis aggregate.

IllustratedReading report

CKT-WAM: Parameter-Efficient Context Knowledge Transfer Between World Action Models

Jiang, Yuhua; Guo, Yijun; Yang, Hongbing +7 authors

WAMs Outside quadrants

7 May 2026

We propose \textbf{CKT-WAM}, a parameter-efficient \textbf{C}ontext \textbf{K}nowledge \textbf{T}ransfer framework that transfers teacher WAM's knowledge into a student WAM through a compact context in the text embedding space, rather than output imitation or dense hidden-state matching. Experiments show that CKT-WAM consistently improves zero-shot generalization and achieves the best overall performance on LIBERO-Plus, reaching 86.1\% total success rate with only 1.17\% trainable parameters, while approaching full fine-tuning performance.

IllustratedReading report

EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields

Yang, Zhaoyang; Jin, Yurun; Qi, Lizhe +2 authors

Benchmarks & simulators Not applicable

7 May 2026

To bridge this gap, we present EA-WM, an Event-Aware Generative World Model that effectively closes the loop between kinematic control and visual perception. To fully exploit this geometrically grounded representation, we introduce event-aware bidirectional fusion blocks that modulate cross-branch attention, capturing object state changes and interaction dynamics.

IllustratedReading report

World Model for Robot Learning: A Comprehensive Survey

Bohan Hou; Gen Li; Jindou Jia +15 authors

Related resources Not applicable

30 Apr 2026

Contribution summary not yet recorded.

IllustratedReading report

Being-H0.7: A Latent World-Action Model from Egocentric Videos

BeingBeyond Team (Hao Luo; Wanpeng Zhang; Yicheng Feng +6 authors

30 Apr 2026

Being-H0.7 trains a robot policy to anticipate useful future information inside latent queries. A future-aware training branch aligns its hidden states with a deployable branch that sees only current context, avoiding visual rollout during control. Strong benchmark and real-robot results support the complete system, while missing component ablations leave the causal contribution of future alignment unresolved (E02–E09, E12, E15).

IllustratedReading report

Motubrain: An Advanced World Action Model for Robot Control

Motubrain Team

30 Apr 2026

Motubrain combines language, video and action streams in a unified generative robot policy. It transfers video priors into relative end-effector control, then uses asymmetric attention and asynchronous action chunks for deployment. Simulation, world-prediction and real-robot evaluations support different capabilities; the autoregressive attention specification remains internally inconsistent.

IllustratedReading report

Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising

Jun Guo; Qiwei Li; Peiyan Li +7 authors

29 Apr 2026

X-WAM adapts a pretrained video diffusion transformer to predict robot actions, future states and multi-view RGB-D observations together. A one-way depth branch adds geometric supervision, while asynchronous denoising releases actions before completing video generation. The paper reports strong simulated manipulation and reconstruction results plus a small physical earphone-packing evaluation. Its central tradeoff is useful spatial supervision without depth decoding during every action step; limited temporal context and delayed control remain unresolved.

IllustratedReading report

Privileged Foresight Distillation: Zero-Cost Future Correction for World Action Models

Pengcheng Fang; Hongli Chen; Xiaohao Cai

28 Apr 2026

Privileged Foresight Distillation (PFD) compares two attention masks on the same world-action backbone, then learns the future-enabled change in action velocity through an output adapter. Deployment uses only the current frame and corrected action denoising. The reported LIBERO mean improves by 1.15 percentage points over reproduced Fast-WAM, with a measured 5.15% cached-context latency overhead; the title's zero-cost wording does not mean zero additional computation.

IllustratedReading report

RL Token: Bootstrapping Online RL with Vision-Language-Action Models

Charles Xu; Jost Tobias Springenberg; Michael Equi +4 authors

VLA Not applicable

24 Apr 2026

Contribution summary not yet recorded.

IllustratedReading report

RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation

Feng Jiang; Yang Chen; Kyle Xu +8 authors

Benchmarks & simulators Not applicable

21 Apr 2026

RoboWM-Bench evaluates whether generated manipulation videos can be converted into robot actions that complete tasks in simulation. Separate human-hand retargeting and robot inverse-dynamics interfaces expose failures hidden by plausible imagery. Reliability tests support these interfaces on real demonstrations, but execution scores still depend on action extraction, reconstructed physics and task-specific checkers.

IllustratedReading report

π_0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities

Physical Intelligence; Bo Ai; Ali Amin +85 authors

16 Apr 2026

Contribution summary not yet recorded.

IllustratedReading report

DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied Tasks

Yueci Deng; Guiliang Liu; Kui Jia

13 Apr 2026

DexWorldModel introduces CLWM, which predicts future DINOv3 features and then generates actions conditioned on that prediction. Shared transformer blocks, separate persistent and speculative memories, and asynchronous denoising connect world prediction to robot execution. EmbodiChain supplies synthetic adaptation data. Reported manipulation results are strong, but protocol omissions and a contradictory flow-time convention limit reproducibility.

IllustratedReading report

AIM: Intent-Aware Unified world action Modeling with Spatial Value Maps

Liaoyuan Fan; Zetian Xu; Chen Cao +3 authors

13 Apr 2026

AIM jointly generates future RGB observations, spatial contact maps and continuous robot actions. A masked mixture-of-transformers architecture makes the predicted maps the action head's only route to future information. Supervised learning uses simulator-derived contact labels; post-training freezes world/value prediction and refines actions using map responses plus task rewards. The paper reports 94.0% Easy and 92.1% Hard success on RoboTwin 2.0, but the small post-training improvement, missing mechanism ablations and inconsistent schematic require careful interpretation.

IllustratedReading report

VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis

Xiaolei Lang; Yang Wang; Yukun Zhou +10 authors

10 Apr 2026

VAG synthesizes robot videos and action sequences from an initial image and instruction. A video diffusion transformer supplies pooled clean-latent predictions to an action U-Net during synchronized denoising. The evidence supports improved action prediction and simulation replay, plus a small real-robot policy-pretraining benefit. It does not establish guaranteed alignment or general closed-loop control.

IllustratedReading report

Learning Vision-Language-Action World Models for Autonomous Driving

Guoqing Wang; Pin Tang; Xiangxuan Ren +3 authors

WAMs Outside quadrants

10 Apr 2026

Contribution summary not yet recorded.

IllustratedReading report

LMGenDrive: Bridging Multimodal Understanding and Generative World Modeling for End-to-End Driving

Hao Shao; Letian Wang; Yang Zhou +5 authors

9 Apr 2026

Contribution summary not yet recorded.

IllustratedReading report

ActiveGlasses: Learning Manipulation with Active Vision from Ego-centric Human Demonstration

Yanwen Zou; Chenyang Shi; Wenye Yu +5 authors

Datasets Not applicable

9 Apr 2026

Contribution summary not yet recorded.

IllustratedReading report

INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling

InSpatio Team; Donghui Shen; Guofeng Zhang +20 authors

Benchmarks & simulators Not applicable

8 Apr 2026

Contribution summary not yet recorded.

IllustratedReading report

Action Images: End-to-End Policy Learning via Multiview Video Generation

Haoyu Zhen; Zixian Gao; Qiao Sun +7 authors

7 Apr 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

JailWAM: Jailbreaking World Action Models in Robot Control

Hanqing Liu; Songping Wang; Jiahuan Long +9 authors

Benchmarks & simulators Not applicable

7 Apr 2026

JailWAM evaluates instruction-induced robot risk by rendering predicted actions as trajectory charts, screening them with a trained vision-language discriminator, and verifying selected candidates in closed-loop simulation. It reports 84.20% human-verified attack success on LingBot-VA, but its cheaper screening pipeline misses some unsafe executions. Success includes motion failure as well as catastrophic risk.

IllustratedReading report

DriveVA: Video Action Models are Zero-Shot Drivers

Mengmeng Liu; Diankun Zhang; Jiuming Liu +7 authors

5 Apr 2026

Contribution summary not yet recorded.

IllustratedReading report

SpatialVAM:Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot Policy

Peiyan Li; Yixiang Chen; Yuan Xu +13 authors

3 Apr 2026

Contribution summary not yet recorded.

IllustratedReading report

UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving

Yongkang Li; Lijun Zhou; Sixu Yan +11 authors

VLA Not applicable

2 Apr 2026

Contribution summary not yet recorded.

IllustratedReading report

DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning

Yang Zhou; Xiaofeng Wang; Hao Shao +8 authors

2 Apr 2026

DriveDreamer-Policy trains a shared multimodal backbone with depth, video and trajectory generators. Ordered query embeddings transfer geometry and future-scene context into planning without requiring rendered depth or video at inference. Navsim scores and controlled modality ablations support useful joint supervision, while depth evaluation against a learned teacher and incomplete runtime details limit the conclusions.

IllustratedReading report

Enhancing Policy Learning with World-Action Model

Yuci Han; Alper Yilmaz

WAMs Outside quadrants

30 Mar 2026

WAM adds inverse action prediction between consecutive encoder embeddings to a DreamerV2 world model, then trains a separate diffusion policy on its frozen latent features. Table III supports 61.7% versus 45.8% average behavioral-cloning success on eight CALVIN tasks. The mechanism is plausible, but inconsistent headline numbers, baseline names and PPO summaries limit stronger conclusions.

IllustratedReading report

ManipArena: A Controlled Benchmark for Diagnosing Generalization in Real-Robot Manipulation

Yu Sun; Meng Cao; Yang Ping +24 authors

Benchmarks & simulators Not applicable

30 Mar 2026

ManipArena evaluates manipulation policies through controlled physical robot trials, task schemas and subgoal scoring. Its strongest lesson is that training recipes and model provenance affect rankings alongside architecture. Language grounding and demonstration selection produce substantial reported gains, but small trial counts, restricted environments and internal reporting inconsistencies limit causal and generalization claims.

IllustratedReading report

Uni-World VLA: Interleaved World Modeling and Planning for Autonomous Driving

Qiqi Liu; Huan Xu; Jingyu Li +5 authors

28 Mar 2026

Contribution summary not yet recorded.

IllustratedReading report

Vega: Learning to Drive with Natural Language Instructions

Sicheng Zuo; Yuxuan Li; Wenzhao Zheng +3 authors

26 Mar 2026

Vega learns instruction-conditioned driving by training trajectory denoising together with future-image denoising. Modality-specific transformers exchange information through global causal attention. InstructScene supplies automatically generated instructions describing recorded driving. The strongest reported NAVSIM v2 score uses best-of-six trajectory selection; NAVSIM v1 results are weaker than leading VLA baselines. Future-prediction ablations support visual supervision, while selected images illustrate instruction sensitivity without measuring general instruction-following reliability.

IllustratedReading report

Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning

Jai Bardhan; Patrik Drozdik; Josef Sivic +1 authors

Benchmarks & simulators Not applicable

26 Mar 2026

Contribution summary not yet recorded.

IllustratedReading report

DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving

Pengxuan Yang; Yupeng Zheng; Deheng Qian +11 authors

WAMs Outside quadrants

25 Mar 2026

Contribution summary not yet recorded.

IllustratedReading report

Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving

Linbo Wang; Yupeng Zheng; Qiang Chen +13 authors

WAMs Outside quadrants

25 Mar 2026

Contribution summary not yet recorded.

IllustratedReading report

Toward Physically Consistent Driving Video World Models under Challenging Trajectories

Jiawei Zhou; Zhenxin Zhu; Lingyi Du +10 authors

Benchmarks & simulators Not applicable

25 Mar 2026

Contribution summary not yet recorded.

IllustratedReading report

VTAM: Video-Tactile-Action Models for Complex Physical Interaction Beyond VLAs

Haoran Yuan; Weigang Yi; Zhenyu Zhang +9 authors

24 Mar 2026

VTAM adapts a video world model to predict camera and tactile streams, then trains a conditional action expert with an auxiliary deformation-derived force target. It reports large gains in three real robot contact tasks. The strongest evidence is task success and a chip ablation; calibrated force accuracy, broad generalization and the claimed gradient mechanism remain unestablished. Method details below preserve inconsistencies between the formulation and implementation appendix.

IllustratedReading report

Do World Action Models Generalize Better than VLAs? A Robustness Study

Zhanguang Zhang; Zhiyuan Li; Behnam Rahmati +11 authors

Benchmarks & simulators Not applicable

23 Mar 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

X-World: Controllable Ego-Centric Multi-Camera World Models for Scalable End-to-End Driving

Chaoda Zheng; Sean Li; Jinhao Deng +9 authors

Benchmarks & simulators Not applicable

20 Mar 2026

Contribution summary not yet recorded.

IllustratedReading report

VAMPO: Policy Optimization for Improving Visual Dynamics in Video Action Models

Zirui Ge; Pengxiang Ding; Baohua Yin +16 authors

19 Mar 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

EVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards

Ruixiang Wang; Qingming Liu; Yueci Deng +3 authors

18 Mar 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

GigaWorld-Policy: An Efficient Action-Centered World–Action Model

Angen Ye; Boyuan Wang; Chaojun Ni +21 authors

WAMs Outside quadrants

18 Mar 2026

Contribution summary not yet recorded.

IllustratedReading report

DreamPlan: Efficient Reinforcement Fine-Tuning of Vision-Language Planners via Video World Models

Emily Yue-Ting Jia; Weiduo Yuan; Tianheng Shi +3 authors

WAMs Outside quadrants

17 Mar 2026

Contribution summary not yet recorded.

IllustratedReading report

Fast-WAM: Do World Action Models Need Test-time Future Imagination?

Tianyuan Yuan; Zibin Dong; Yicheng Liu +1 authors

WAMs Outside quadrants

17 Mar 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresight

Haodong Yan; Zhide Zhong; Jiaguan Zhu +10 authors

17 Mar 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

Bridging Scene Generation and Planning: Driving with World Model via Unifying Vision and Motion Representation

Xingtai Gui; Meijie Zhang; Tianyi Yan +5 authors

WAMs Outside quadrants

16 Mar 2026

Contribution summary not yet recorded.

IllustratedReading report

V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning

Lorenzo Mur-Labadia; Matthew Muckley; Amir Bar +6 authors

Components of WAMs Not applicable

15 Mar 2026

Contribution summary not yet recorded.

IllustratedReading report

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

Lucas Maes; Quentin Le Lidec; Damien Scieur +2 authors

WAMs Outside quadrants

13 Mar 2026

Contribution summary not yet recorded.

IllustratedReading report

DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control

Teli Ma; Jia Zheng; Zifan Wang +4 authors

11 Mar 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

World2Act: Latent Action Post-Training from World Model Dynamics

An Dinh Vuong; Tuan Van Vo; Abdullah Sohail +6 authors

WAMs Outside quadrants

11 Mar 2026

Contribution summary not yet recorded.

IllustratedReading report

SAMoE-VLA: A Scene Adaptive Mixture-of-Experts Vision-Language-Action Model for Autonomous Driving

Zihan You; Hongwei Liu; Chenxu Dang +4 authors

9 Mar 2026

Contribution summary not yet recorded.

IllustratedReading report

MEM: Multi-Scale Embodied Memory for Vision Language Action Models

Marcel Torne; Karl Pertsch; Homer Walke +14 authors

VLA Not applicable

4 Mar 2026

Contribution summary not yet recorded.

IllustratedReading report

Unifying Language-Action Understanding and Generation for Autonomous Driving

Xinyang Wang; Qian Liu; Wenjie Ding +7 authors

VLA Not applicable

2 Mar 2026

Contribution summary not yet recorded.

IllustratedReading report

Self-Correcting VLA: Online Action Refinement via Sparse World Imagination

Chenyv Liu; Wentao Tan; Lei Zhu +4 authors

25 Feb 2026

SC-VLA adds progress and end-effector-change predictions to a GR00T N1.5-based flow policy, then freezes it and trains a SAC residual controller. Predicted motion supplies a directional reward whose influence decreases with predicted progress. Simulation supports both stages; physical ARX5 trials test only the predictive base policy. The evidence supports improved executed manipulation under the reported protocols, with unresolved reward and evaluation details.

IllustratedReading report

EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data

Ruijie Zheng; Dantong Niu; Yuqi Xie +12 authors

VLA Not applicable

18 Feb 2026

Contribution summary not yet recorded.

IllustratedReading report

Learning to unfold cloth: Scaling up world models to deformable object manipulation

Jack Rome; Stephen James; Subramanian Ramamoorthy

WAMs Outside quadrants

18 Feb 2026

Contribution summary not yet recorded.

IllustratedReading report

Factored Latent Action World Models

Zizhao Wang; Chang Shi; Jiaheng Hu +4 authors

Related resources Not applicable

18 Feb 2026

FLAM learns a video world model whose slots each carry a latent action while sharing interaction-aware dynamics networks. Prediction-trained factorization improves rollouts supplied with future-inferred actions and can supply pseudo action labels for behavior cloning. Its strongest evidence concerns multi-entity video modeling; downstream control is evaluated separately in Procgen.

IllustratedReading report

WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL

Zhennan Jiang; Shangqing Zhou; Yutong Jiang +11 authors

WAMs Outside quadrants

15 Feb 2026

Contribution summary not yet recorded.

IllustratedReading report

LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion

Jiangran Lyu; Kai Liu; Xuheng Zhang +20 authors

WAMs Pending verification

12 Feb 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning

GigaBrain Team; Boyuan Wang; Bohan Li +23 authors

WAMs Outside quadrants

12 Feb 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

RISE: Self-Improving Robot Policy with Compositional World Model

Jiazhi Yang; Kunyang Lin; Jinwei Li +10 authors

WAMs Outside quadrants

11 Feb 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

VideoWorld 2: Learning Transferable Knowledge from Real-world Videos

Zhongwei Ren; Yunchao Wei; Xiao Yu +5 authors

10 Feb 2026

VideoWorld 2 learns discrete visual-dynamics codes with a pretrained diffusion appearance prior, then trains an autoregressive transformer to predict those codes. It improves generated long-horizon craft sequences and transfers latent pretraining to a separately action-supervised CALVIN policy. Its evidence supports benchmark-specific transfer; generated craft success, simulator control and complete appearance disentanglement remain distinct claims.

IllustratedReading report

VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model

Jingwen Sun; Wenyao Zhang; Zekun Qi +6 authors

10 Feb 2026

Contribution summary not yet recorded.

IllustratedReading report

WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models

Yu Shang; Zhuohang Li; Yiding Ma +18 authors

Benchmarks & simulators Not applicable

9 Feb 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy

Xiaokang Liu; Zechen Bai; Hai Ci +2 authors

WAMs Outside quadrants

6 Feb 2026

Contribution summary not yet recorded.

IllustratedReading report

Visuo-Tactile World Models

Carolina Higuera; Sergio Arnaud; Byron Boots +3 authors

WAMs Outside quadrants

5 Feb 2026

Contribution summary not yet recorded.

IllustratedReading report

HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos

Yinhuai Wang; Qihan Zhao; Yuen Fui Lau +6 authors

Datasets Not applicable

2 Feb 2026

Contribution summary not yet recorded.

IllustratedReading report

Causal World Modeling for Robot Control

Lin Li; Qihang Zhang; Yiming Luo +9 authors

29 Jan 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning

Moo Jin Kim; Yihuai Gao; Tsung-Yi Lin +8 authors

22 Jan 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

UniDrive-WM: Unified Understanding, Planning and Generation World Model for Autonomous Driving

Zhexiao Xiong; Xin Ye; Burhan Yaman +5 authors

WAMs Pending verification

7 Jan 2026

Contribution summary not yet recorded.

IllustratedReading report

Wow, wo, val! A Comprehensive Embodied World Model Evaluation Turing Test

Chun-Kai Fan; Xiaowei Chi; Xiaozhu Ju +18 authors

Benchmarks & simulators Not applicable

7 Jan 2026

WoW-World-Eval tests whether instruction-conditioned robot videos are visually convincing, task-correct, physically plausible and usable for action extraction. Its 609-sample benchmark combines automated metrics, human judgments and a separate GC-IDM robot-execution test. Hailuo leads the reported aggregate video score, while WoW-wan leads physical execution. The central lesson is that a plausible imagined manipulation and an executable one are distinct outcomes; calibration and evaluator dependence constrain how broadly the scores can be interpreted.

IllustratedReading report

CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos

Chubin Zhang; Jianan Wang; Zifeng Gao +5 authors

VLA Not applicable

7 Jan 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation

Wenlong Huang; Yu-Wei Chao; Arsalan Mousavian +4 authors

WAMs Outside quadrants

7 Jan 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

Motus: A Unified Latent Action World Model

Hongzhe Bi; Hengkai Tan; Shenghao Xie +13 authors

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

Vtla: Vision-tactile-language-action model with preference learning for insertion manipulation

Chaofan Zhang; Peng Hao; Xiaoge Cao +3 authors

VLA Not applicable

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

Dyna-2: A 1-million-hour scaling law for world-action models

Dyna Robotics

WAMs Outside quadrants

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving

Jianhua Han; Meng Tian; Jiangtong Zhu +16 authors

VLA Not applicable

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

Ctrl-World: A Controllable Generative World Model for Robot Manipulation

Yanjiang Guo; Lucy Xiaoyang Shi; Jianyu Chen +1 authors

Benchmarks & simulators Not applicable

Year 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

Towards Generalist Embodied AI: A Survey on World Models for VLA Agents

Wentao Tan; Lei Zhu; Bowen Wang +6 authors

Related resources Not applicable

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

MonoDream: Monocular Vision-Language Navigation with Panoramic Dreaming

Shuo Wang; Yongcai Wang; Zhaoxin Fan +8 authors

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model

Xingcheng Zhou; Xuyuan Han; Feng Yang +3 authors

VLA Not applicable

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

DriveLaW: Unifying Planning and Video Generation in a Latent Driving World

Tianze Xia; Yongkang Li; Lijun Zhou +9 authors

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation

Tianxing Chen; Zanxin Chen; Baijun Chen +23 authors

Datasets Not applicable

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

Hierarchical Latent Action Model

Hanjung Kim; Lerrel Pinto; Seon Joo Kim

VLA Not applicable

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

DreamDojo: A Real-Time Robot World Model from Large-Scale Human Videos

Shenyuan Gao; William Liang; Kaiyuan Zheng +27 authors

WAMs Not applicable

Year 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation

Zijian Song; Qichang Li; Sihan Qin +4 authors

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

WorldGym: World Model as An Environment for Policy Evaluation

Julian Quevedo; Ansh Kumar Sharma; Yixiang Sun +3 authors

Benchmarks & simulators Not applicable

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

AutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture-of-Transformers for End-to-End Autonomous Driving

Wenhui Huang; Songyan Zhang; Qihang Huang +6 authors

VLA Not applicable

Year 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model

Yanjiang Guo; Tony Lee; Lucy Xiaoyang Shi +3 authors

WAMs Outside quadrants

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

ViPRA: Video Prediction for Robot Actions

Sandeep Routray; Hengkai Pan; Unnat Jain +2 authors

Year 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT

Xiaotao Hu; Mingkai Jia; Xiaoyang Guo +3 authors

Year 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Driving

Feiyang jia; Lin Liu; Ziying Song +4 authors

WAMs Outside quadrants

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation

TRI LBM Team; Jose Barreiros; Andrew Beaulieu +79 authors

VLA Not applicable

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving

Yingyan Li; Shuyao Shang; Weisong Liu +10 authors

WAMs Outside quadrants

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video

Ryan Hoque; Peide Huang; David J. Yoon +2 authors

Datasets Not applicable

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving

Yang Zhou; Hao Shao; Letian Wang +3 authors

Benchmarks & simulators Not applicable

Year 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

WMPO: World Model-based Policy Optimization for Vision-Language-Action Models

Fangqi Zhu; Zhengyang Yan; Zicong Hong +3 authors

WAMs Outside quadrants

Year 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving

Shuyao Shang; Bing Zhan; Yunfei Yan +9 authors

Year 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

DINOv3

Oriane Siméoni; Huy V. Vo; Maximilian Seitzer +23 authors

Components of WAMs Not applicable

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-Language-Action Model

Fuhao Li; Wenxuan Song; Han Zhao +5 authors

VLA Not applicable

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

Learning Latent Action World Models In The Wild

Quentin Garrido; Tushar Nagarajan; Basile Terver +3 authors

WAMs Not applicable

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots

Chenhao Li; Andreas Krause; Marco Hutter

WAMs Outside quadrants

Year 2026

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models

Zhilong Zhang; Haoxiang Ren; Yihao Sun +6 authors

WAMs Outside quadrants

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

Interactive World Simulator for Robot Policy Training and Evaluation

Yixuan Wang; Rhythm Syed; Fangyu Wu +7 authors

Benchmarks & simulators Not applicable

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

World Action Models are Zero-shot Policies

Seonghyeon Ye; Yunhao Ge; Kaiyuan Zheng +33 authors

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-and-Language Navigation

Meng Wei; Chenyang Wan; Jiaqi Peng +8 authors

VLA Not applicable

Year 2026

Contribution summary not yet recorded.

IllustratedReading report

Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow

Karthik Dharmarajan; Wenlong Huang; Jiajun Wu +2 authors

WAMs Outside quadrants

31 Dec 2025

Dream2Flow converts generated human-interaction videos into 3D object trajectories, then uses domain-specific optimization or reinforcement learning to make a robot realize them. Its central benefit is an object-level interface across embodiments; its reliability still depends on video geometry, tracking, contact assumptions and the downstream controller.

IllustratedReading report

Act2Goal: From World Model To General Goal-conditioned Policy

Pengfei Zhou; Liliang Chen; Shengcong Chen +5 authors

29 Dec 2025

Contribution summary not yet recorded.

IllustratedReading report

CoVAR: Co-generation of Video and Action for Robotic Manipulation via Multi-Modal Diffusion

Liudi Yang; Yang Bai; George Eskandar +5 authors

17 Dec 2025

CoVAR co-generates instruction-conditioned video and robot actions through separate, interacting diffusion transformers. Bridge Attention connects a pretrained video branch to an action branch; a UNet decodes actions, with an additional refinement model for LIBERO90. Reported simulation and UR5 successes support the complete system, while refinement dependence, incomplete evaluation details, and roughly four-second sequence generation limit broader conclusions.

IllustratedReading report

mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs

Jonas Pai; Liam Achenbach; Victoriano Montesinos +3 authors

17 Dec 2025

Contribution summary not yet recorded.

IllustratedReading report

World Models for Learning Dexterous Hand-Object Interactions from Human Videos

Raktim Gautam Goswami; Amir Bar; David Fan +6 authors

WAMs Outside quadrants

15 Dec 2025

Contribution summary not yet recorded.

IllustratedReading report

WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World

Ao Liang; Lingdong Kong; Tianyi Yan +19 authors

Benchmarks & simulators Not applicable

11 Dec 2025

WorldLens evaluates driving video generators through appearance, reconstructability, planner behavior, perception and human judgment. Its strongest lesson is that favorable image metrics coexist with poor closed-loop route completion. A separate LoRA-trained critic learns score-and-rationale outputs from human annotations; its generalization evidence remains qualitative.

IllustratedReading report

VideoVLA: Video Generators Can Be Generalizable Robot Manipulators

Yichao Shen; Fangyun Wei; Zhiying Du +5 authors

7 Dec 2025

VideoVLA adapts CogVideoX-5B into a robot policy that jointly denoises future video latents and executable action chunks, conditioned on language and the current image. Its clearest gains concern novel objects and skills transferred between embodiments. Video supervision matters strongly in the reported ablations, but imagined success exceeds executed success and deployment remains slow.

IllustratedReading report

MIND-V: Hierarchical World Model for Long-Horizon Robotic Manipulation with RL-based Physical Alignment

Ruicheng Zhang; Mingyang Zhang; Jun Zhou +6 authors

Benchmarks & simulators Not applicable

7 Dec 2025

Contribution summary not yet recorded.

IllustratedReading report

MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Driving

Bin Sun; Yaoguang Cao; Yan Wang +8 authors

WAMs Outside quadrants

4 Dec 2025

MindDrive couples action-conditioned BEV scene prediction with anchor refinement and a VLM trajectory scorer. Its main contribution is the connection between future-aware candidate generation and selection. NAVSIM scores support planning gains, while incomplete training specifications and inconsistent result reporting limit reproducibility.

IllustratedReading report

Video2Act: A Dual-System Video Diffusion Policy with Robotic Spatio-Motional Modeling

Yueru Jia; Jiaming Liu; Shengbang Liu +7 authors

2 Dec 2025

Video2Act turns observed video into conditioning for a separate robot action policy. Sobel filtering emphasizes spatial structure in video-model features, while temporal Fourier filtering emphasizes motion. A slow video network refreshes these representations for a faster diffusion action head. The strongest evidence is improved executed manipulation on RoboTwin and a small real-robot evaluation; the speed claims require separating action-chunk throughput from fresh-feedback control.

IllustratedReading report

LatBot: Distilling Universal Latent Actions for Vision-Language-Action Models

Zuolei Li; Xingyu Gao; Xiaofan Wang +1 authors

28 Nov 2025

LatBot learns scene and motion latents from language-conditioned robot and human manipulation videos, supervises them through future-image and physical-action decoding, then distills them into a VLA student. An action expert converts the student's features into executable commands. The strongest evidence concerns downstream manipulation success; universal physical understanding and preserved reasoning remain broader interpretations of these results (e03–e06, e12–e16).

IllustratedReading report

GigaWorld-0: World Models as Data Engine to Empower Embodied AI

GigaWorld Team; Angen Ye; Boyuan Wang +22 authors

Datasets Not applicable

25 Nov 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

Learning Massively Multitask World Models for Continuous Control

Nicklas Hansen; Hao Su; Xiaolong Wang

WAMs Outside quadrants

24 Nov 2025

Newt extends TD-MPC2 into a language-conditioned agent that learns latent dynamics from demonstrations and online interaction across MMBench. Its practical recipe pretrains the world model and policy prior, retains action supervision, and uses the model to plan. It improves over the evaluated multitask baselines, but specialist policies remain stronger and long open-loop execution is uneven. The evidence concerns simulated, predominantly state-based control.

IllustratedReading report

RynnVLA-002: A Unified Vision-Language-Action and World Model

Jun Cen; Siteng Huang; Yuqian Yuan +11 authors

21 Nov 2025

RynnVLA-002 finetunes a shared Chameleon backbone for action prediction and action-conditioned image prediction, then adds a parallel continuous-action head. Its strongest evidence is mutual training benefit: better executed policies and better held-out visual predictions. Policy inference uses no imagined-image rollout. The reported 97.4% LIBERO average is competitive, while physical evidence is limited to SO100 pick-and-place.

IllustratedReading report

Dexterity from Smart Lenses: Multi-Fingered Robot Manipulation with In-the-Wild Human Demonstrations

Irmak Guzey; Haozhi Qi; Julen Urain +10 authors

Related resources Not applicable

20 Nov 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

π^*_0.6: a VLA That Learns From Experience

Physical Intelligence; Ali Amin; Raichelle Aniceto +53 authors

VLA Not applicable

18 Nov 2025

Contribution summary not yet recorded.

IllustratedReading report

Scalable Policy Evaluation with Video World Models

Wei-Cheng Tseng; Jinwei Gu; Qinsheng Zhang +4 authors

Benchmarks & simulators Not applicable

14 Nov 2025

Contribution summary not yet recorded.

IllustratedReading report

PAN: A World Model for General, Interactable, and Long-Horizon World Simulation

PAN Team; Jiannan Xiang; Yi Gu +31 authors

Benchmarks & simulators Not applicable

12 Nov 2025

Contribution summary not yet recorded.

IllustratedReading report

Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model

John Won; Kyungmin Lee; Huiwon Jang +2 authors

31 Oct 2025

DUST augments a frozen vision-language backbone with jointly denoised actions and future visual embeddings. Separate streams exchange information through attention; independent noise levels and unequal sampling budgets accommodate their different dynamics. Controlled comparisons support improved manipulation, but do not establish general causal world understanding.

IllustratedReading report

π_RL: Online RL Fine-tuning for Flow-based Vision-Language-Action Models

Kang Chen; Zhihao Liu; Tonghe Zhang +11 authors

VLA Not applicable

29 Oct 2025

Contribution summary not yet recorded.

IllustratedReading report

World Simulation with Video Foundation Models for Physical AI

NVIDIA; :; Arslan Ali +87 authors

Components of WAMs Not applicable

28 Oct 2025

Contribution summary not yet recorded.

IllustratedReading report

GigaBrain-0: A World Model-Powered Vision-Language-Action Model

GigaBrain Team; Angen Ye; Boyuan Wang +24 authors

VLA Not applicable

22 Oct 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models

Senyu Fei; Siyin Wang; Junhao Shi +10 authors

Benchmarks & simulators Not applicable

15 Oct 2025

Contribution summary not yet recorded.

IllustratedReading report

Ego-Vision World Model for Humanoid Contact Planning

Hang Liu; Yuman Gao; Sangli Teng +5 authors

WAMs Outside quadrants

13 Oct 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

Generative World Modelling for Humanoids: 1X World Model Challenge Technical Report

Riccardo Mereu; Aidan Scannell; Yuxin Hou +6 authors

Benchmarks & simulators Not applicable

8 Oct 2025

Team Revontuli uses two separate, state-conditioned predictors: a LoRA-adapted Wan video model for future RGB frames and a spatio-temporal Transformer for future discrete tokens. Both lead the reported challenge leaderboard, but their scores measure conditional prediction rather than executed humanoid control.

IllustratedReading report

MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Training

Haoyun Li; Ivan Zhang; Runqi Ouyang +12 authors

Datasets Not applicable

26 Sept 2025

MimicDreamer converts human demonstrations into robot-looking videos paired with retargeted actions, then post-trains a separate π0 policy. The contribution is training-data alignment across viewpoint, embodiment and appearance. Physical-task results improve with added synthetic demonstrations, but real-robot supervision remains part of the evaluated pipeline and several headline summaries conflict with the tables.

IllustratedReading report

MoWM: Mixture-of-World-Models for Embodied Planning via Latent-to-Pixel Feature Modulation

Yangcheng Yu; Xin Jin; Yu Shang +4 authors

26 Sept 2025

Contribution summary not yet recorded.

IllustratedReading report

LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE

Yu Shang; Lei Jin; Yiding Ma +4 authors

Benchmarks & simulators Not applicable

26 Sept 2025

Contribution summary not yet recorded.

IllustratedReading report

World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulation

Zhennan Jiang; Kai Liu; Yuxin Qin +6 authors

WAMs Outside quadrants

23 Sept 2025

Contribution summary not yet recorded.

IllustratedReading report

Latent Action Pretraining Through World Modeling

Bahey Tharwat; Yara Nasser; Ali Abouzeid +1 authors

WAMs Not applicable

22 Sept 2025

Contribution summary not yet recorded.

IllustratedReading report

Spatial Policy: Guiding Visuomotor Robotic Manipulation with Spatial-Aware Modeling and Reasoning

Yijun Liu; Yuwei Liu; Yuan Meng +8 authors

21 Aug 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

MoVieDrive: Urban Scene Synthesis with Multi-Modal Multi-View Video Diffusion Transformer

Guile Wu; David Huang; Dongfeng Bai +1 authors

Benchmarks & simulators Not applicable

20 Aug 2025

Contribution summary not yet recorded.

IllustratedReading report

IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model

Anqing Jiang; Yu Gao; Yiru Wang +11 authors

WAMs Outside quadrants

7 Aug 2025

Contribution summary not yet recorded.

IllustratedReading report

Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation

Yue Liao; Pengfei Zhou; Siyuan Huang +11 authors

WAMs Outside quadrants

7 Aug 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

Video Generators are Robot Policies

Junbang Liang; Pavel Tokmakov; Ruoshi Liu +4 authors

1 Aug 2025

Contribution summary not yet recorded.

IllustratedReading report

Vidar: Embodied Video Diffusion Model for Generalist Manipulation

Yao Feng; Hengkai Tan; Xinyi Mao +5 authors

17 Jul 2025

Vidar adapts an embodied video generator to a target bimanual robot, then converts predicted imagery into controls using a separately trained masked inverse dynamics model. Low-demonstration real-world results and component ablations support this design; action observability, open-loop execution, and substantial prior training constrain its generality.

IllustratedReading report

StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling

Meng Wei; Chenyang Wan; Xiqian Yu +9 authors

VLA Not applicable

7 Jul 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

Critique of World Model

Eric Xing; Mingkai Deng; Jinyu Hou

Foundational work Not applicable

7 Jul 2025

Contribution summary not yet recorded.

IllustratedReading report

DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge

Wenyao Zhang; Hongsi Liu; Zekun Qi +11 authors

6 Jul 2025

DreamVLA trains a shared backbone to anticipate motion-relevant regions, depth and semantic features, then conditions action diffusion on its latent predictions. Explicit visual decoders disappear at inference. It reports 4.44 completed instructions on CALVIN ABC-D and 76.7% real-robot success under an attempt-limited protocol. Its lesson is selective forecasting, tempered by unresolved mask, configuration and table inconsistencies.

IllustratedReading report

RoboScape: Physics-informed Embodied World Model

Yu Shang; Xin Zhang; Yinzhou Tang +4 authors

Benchmarks & simulators Not applicable

29 Jun 2025

RoboScape predicts action-conditioned robotic RGB and depth videos using coupled autoregressive branches. Depth-feature feedback and motion-selected keypoint supervision aim to improve geometry and interaction dynamics. Reported benefits include stronger video metrics, useful synthetic policy-training data, and correlated simulator-based policy evaluation; the ablations expose tradeoffs, and physical robot deployment remains future work.

IllustratedReading report

WorldVLA: Towards Autoregressive Action World Model

Jun Cen; Chaohui Yu; Hangjie Yuan +9 authors

26 Jun 2025

Contribution summary not yet recorded.

IllustratedReading report

AMPLIFY: Actionless Motion Priors for Robot Learning from Videos

Jeremy A. Collins; Loránd Cheng; Kunal Aneja +3 authors

17 Jun 2025

AMPLIFY learns a compact vocabulary of visual motion from point tracks, predicts that motion from an image and task instruction, and translates it into robot actions through a separate inverse model. Its strongest evidence concerns scarce target-task action labels, including transfer where target-task videos remain available. Better track prediction and physical task completion are evaluated separately.

IllustratedReading report

V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning

Mido Assran; Adrien Bardes; David Fan +27 authors

WAMs Outside quadrants

11 Jun 2025

Contribution summary not yet recorded.

IllustratedReading report

Seedance 1.0: Exploring the Boundaries of Video Generation Models

Yu Gao; Haoyuan Guo; Tuyen Hoang +41 authors

Components of WAMs Not applicable

10 Jun 2025

Contribution summary not yet recorded.

IllustratedReading report

3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model

Hongyan Zhi; Peihao Chen; Siyuan Zhou +4 authors

WAMs Outside quadrants

6 Jun 2025

3DFlowAction learns instruction-conditioned object trajectories from human and robot videos, checks a rendered endpoint with GPT-4o, and converts accepted flow into robot poses through grasp selection and optimization. Its four-task physical evaluation reports 70% success, but transfer depends on rigid grasp geometry and follows task-specific human-video fine-tuning.

IllustratedReading report

Towards a Generalizable Bimanual Foundation Policy via Flow-based Video Prediction

Chenyou Fan; Fangzheng Yan; Chenjia Bai +4 authors

30 May 2025

CogRobot adapts video diffusion to bimanual control through three learned components: instruction-conditioned flow prediction, flow-conditioned RGB prediction, and a task-specific goal-reaching action policy. Flow offers an intermediate description of motion without requiring action labels for the video models. The strongest physical result is Pull Box success of 0.75 versus 0.05 for DP, but the evidence does not establish a universal action policy or broad unseen-task transfer (e02-framing, e05-video, e06-controller, e09-real, e13-limit).

IllustratedReading report

RoboTransfer: Controllable Geometry-Consistent Video Diffusion for Manipulation Policy Transfer

Liu Liu; Xiaofeng Wang; Guosheng Zhao +7 authors

Datasets Not applicable

29 May 2025

RoboTransfer augments robot demonstrations by changing their visual appearance while conditioning video diffusion on the demonstrated geometry. Jointly encoded camera views, metric depth, normals and separate background/object references support multi-view synthesis. A separately trained ACT policy benefits from the augmented observations on two physical manipulation tasks. This is evidence for offline data augmentation, with remaining uncertainty about statistical reliability and physical fidelity.

IllustratedReading report

Learning Generalizable Robot Policy with Human Demonstration Video as a Prompt

Xiang Zhu; Yichen Liu; Hezhong Li +1 authors

Related resources Not applicable

27 May 2025

A human demonstration video conditions a frozen video model whose features guide a separate diffusion policy for an Xhand robot. Human hand motions are reconstructed and retargeted into the policy's action space, allowing human demonstrations to supervise action learning. The reported transfer concerns objects and skills absent from robot training demonstrations but present in human training data; it does not establish learning an entirely untrained skill from the inference prompt alone.

IllustratedReading report

WorldEval: World Model as Real-World Robot Policies Evaluator

Yaxuan Li; Yichen Zhu; Junjie Wen +2 authors

Benchmarks & simulators Not applicable

25 May 2025

WorldEval estimates robot-policy rankings by turning internal policy embeddings into generated manipulation videos and judging their outcomes. Policy2Vec conditions a separately adapted WAN 2.1 simulator; Gemini-2.0 supplies success labels. Paired experiments support relative-ranking usefulness on the tested tabletop setup, while imperfect action fidelity, checkpoint-distribution dependence and inconsistent source reporting limit stronger conclusions.

IllustratedReading report

ProphetDWM: A Driving World Model for Rolling Out Future Actions and Videos

Xiaodong Wang; Peixi Peng

24 May 2025

Contribution summary not yet recorded.

IllustratedReading report

FLARE: Robot Learning with Implicit World Modeling

Ruijie Zheng; Jing Wang; Scott Reed +18 authors

21 May 2025

FLARE trains a flow-matching robot policy to match future observation embeddings inside its action-denoising transformer. Compact, action-trained visual-language targets supply an auxiliary learning signal, including from action-free human videos. Simulation and real-robot improvements support this training recipe; they do not establish an explicit planner or calibrated world simulator.

IllustratedReading report

EnerVerse-AC: Envisioning Embodied Environments with Action Condition

Yuxin Jiang; Shengcong Chen; Siyuan Huang +8 authors

Benchmarks & simulators Not applicable

14 May 2025

EVAC turns robot action sequences into future camera observations using a video diffusion model. Spatial pose maps, temporal action differences and camera rays condition the generated environment. A separate policy can interact with that environment for evaluation, or learn from synthetic trajectories. The strongest evidence is a small policy-data augmentation experiment and agreement with real-robot evaluation trends; physical accuracy remains incompletely measured.

IllustratedReading report

EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models

Yue Hu; Siyuan Huang; Yue Liao +5 authors

Benchmarks & simulators Not applicable

14 May 2025

EWMBench evaluates instruction-conditioned robot videos through scene consistency, end-effector motion, and semantics. Its seven-model comparison favors domain-adapted generators, while controlled trajectory corruptions expose why static-looking plausibility is insufficient. These are offline video-evaluation results, with unresolved reporting inconsistencies, rather than demonstrations of executed robot control.

IllustratedReading report

UniVLA: Learning to Act Anywhere with Task-centric Latent Actions

Qingwen Bu; Yanting Yang; Jisong Cai +5 authors

9 May 2025

UniVLA learns a discrete action vocabulary from language-annotated videos, teaches a vision-language policy to predict that vocabulary, and adapts a visual-conditioned head to physical controls. Its distinguishing idea is to separate task-relevant motion from distracting changes before policy pretraining. Strong manipulation and navigation results support transfer, but deployment still needs action-labeled adaptation; future-observation prediction trains the latent representation rather than serving as the evaluated inference-time planner (e-lam, e-policy, e-decode, e-libero, e-nav, e-limitations).

IllustratedReading report

CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations

Anthony Liang; Pavel Czempin; Matthew M. Hong +4 authors

Related resources Not applicable

8 May 2025

CLAM learns continuous action codes from robot observation transitions, grounds them with limited action-labeled data, then imitates expert videos in that latent space. Deployment uses a policy and action decoder; future-observation prediction serves training. Its strongest evidence concerns action-label scarcity within one robot embodiment, with several unresolved protocol details.

IllustratedReading report

Learned Perceptive Forward Dynamics Model for Safe and Platform-aware Robotic Navigation

Pascal Roth; Jonas Frey; Cesar Cadena +1 authors

WAMs Outside quadrants

27 Apr 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulation

Wenxuan Li; Hang Zhao; Zhiyuan Yu +4 authors

WAMs Outside quadrants

23 Apr 2025

Contribution summary not yet recorded.

IllustratedReading report

Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets

Chuning Zhu; Raymond Yu; Siyuan Feng +3 authors

3 Apr 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models

Qingqing Zhao; Yao Lu; Moo Jin Kim +12 authors

27 Mar 2025

CoT-VLA makes a 7B multimodal model generate a future subgoal image before predicting a robot action chunk. The shared model learns image prediction from demonstrations and captioned videos, while action supervision requires demonstrations. Experiments support useful goal conditioning and stronger average manipulation performance, with uneven task gains, substantial inference overhead and reporting inconsistencies. Visual chain of thought here means an explicit predicted image used for control; general reasoning is not independently established.

IllustratedReading report

GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving

Lloyd Russell; Anthony Hu; Lorenzo Bertoni +4 authors

Benchmarks & simulators Not applicable

26 Mar 2025

Contribution summary not yet recorded.

IllustratedReading report

Wan: Open and Advanced Large-Scale Video Generative Models

Team Wan; Ang Wang; Baole Ai +59 authors

Components of WAMs Not applicable

26 Mar 2025

Contribution summary not yet recorded.

IllustratedReading report

Gemma 3 Technical Report

Gemma Team; Aishwarya Kamath; Johan Ferret +213 authors

Components of WAMs Not applicable

25 Mar 2025

Contribution summary not yet recorded.

IllustratedReading report

GR00T N1: An Open Foundation Model for Generalist Humanoid Robots

NVIDIA; :; Johan Bjorck +40 authors

VLA Not applicable

18 Mar 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control

NVIDIA; :; Hassan Abu Alhaija +38 authors

Components of WAMs Not applicable

18 Mar 2025

Contribution summary not yet recorded.

IllustratedReading report

LUMOS: Language-Conditioned Imitation Learning with World Models

Iman Nematollahi; Branton DeMoss; Akshay L Chandra +3 authors

WAMs Outside quadrants

13 Mar 2025

LUMOS trains a language-guided manipulation policy by practicing inside a world model learned from offline robot play. Frozen recurrent dynamics support actor-critic learning with expert-latent matching rewards; hindsight plans and language alignment organize behavior. CALVIN and physical tabletop experiments support this combination, with modest gains over adapted HULC and larger component-ablation losses. Transfer means deployment after learning from that environment’s offline data, without online policy fine-tuning.

IllustratedReading report

Unified Video Action Model

Shuang Li; Yihuai Gao; Dorsa Sadigh +1 authors

28 Feb 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

Moo Jin Kim; Chelsea Finn; Percy Liang

VLA Not applicable

27 Feb 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

VaViM and VaVAM: Autonomous Driving through Video Generative Modeling

Florent Bartoccioni; Elias Ramzi; Victor Besnier +14 authors

WAMs Outside quadrants

21 Feb 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

The Role of World Models in Shaping Autonomous Driving: A Comprehensive Survey

Sifan Tu; Xin Zhou; Dingkang Liang +4 authors

Related resources Not applicable

14 Feb 2025

Contribution summary not yet recorded.

IllustratedReading report

VILP: Imitation Learning with Latent Video Planning

Zhengtong Xu, Qiang Qiu, Yu She

3 Feb 2025

VILP learns observation-conditioned future videos in a compressed latent space, decodes them, and maps adjacent frames to actions through a separate low-level policy. This makes short-horizon video planning practical on the tested tasks and lets task videos supply information beyond scarce action labels. Simulation gains depend on data and evaluation protocol; real-robot evidence comprises 15 trials per method.

IllustratedReading report

VideoWorld: Exploring Knowledge Learning from Unlabeled Videos

Zhongwei Ren; Yunchao Wei; Xun Guo +4 authors

16 Jan 2025

VideoWorld predicts compact multi-step dynamics codes alongside video frames, then converts predictions into task operations. On rendered 9×9 Go and simulated robot tasks, this representation substantially improves over video-only prediction. Expert-curated training data, language conditioning and a separately supervised robot action decoder qualify the broader claim of learning solely from unlabeled videos.

IllustratedReading report

FAST: Efficient Action Tokenization for Vision-Language-Action Models

Karl Pertsch; Kyle Stachowicz; Brian Ichter +6 authors

Components of WAMs Not applicable

16 Jan 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

RoboHorizon: An LLM-Assisted Multi-View World Model for Long-Horizon Robotic Manipulation

Zixuan Chen; Jing Huo; Yangtao Chen +1 authors

WAMs Outside quadrants

11 Jan 2025

Contribution summary not yet recorded.

IllustratedReading report

EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation

Siyuan Huang; Liliang Chen; Pengfei Zhou +8 authors

3 Jan 2025

EnerVerse learns instruction-conditioned, multi-view future-video representations, then conditions a separate action diffusion head on their backbone features. Sparse history supports long tasks; an offline 4D Gaussian Splatting loop refines training videos. Its strongest benchmark average uses depth-rendered auxiliary views, while physical block placement exposes an instruction-following weakness.

IllustratedReading report

Learning Robot Manipulation from Audio World Models

Fan Zhang; Michael Gienger

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation

Guosheng Zhao; Xiaofeng Wang; Zheng Zhu +4 authors

Benchmarks & simulators Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

A review of learning-based dynamics models for robotic manipulation

Bo Ai; Stephen Tian; Haochen Shi +7 authors

Related resources Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

DreamGen: Unlocking Generalization in Robot Learning through Video World Models

Joel Jang; Seonghyeon Ye; Zongyu Lin +25 authors

Datasets Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

Latent Action Pretraining from Videos

Seonghyeon Ye; Joel Jang; Byeongguk Jeon +13 authors

Components of WAMs Not applicable

Year 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning

Jianlan Luo; Charles Xu; Jeffrey Wu +1 authors

Foundational work Not applicable

Year 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

Mean Flows for One-step Generative Modeling

Zhengyang Geng; Mingyang Deng; Xingjian Bai +2 authors

Foundational work Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

Helix: A Vision-Language-Action Model for Generalist Humanoid Control

Figure AI

VLA Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

AdaWorld: Learning Adaptable World Models with Latent Actions

Shenyuan Gao; Siyuan Zhou; Yilun Du +2 authors

Foundational work Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models

Weixin Liang; Lili Yu; Liang Luo +8 authors

Components of WAMs Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry

Chunran Zheng; Wei Xu; Zuhao Zou +11 authors

Related resources Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

RLVR-World: Training World Models with Reinforcement Learning

Jialong Wu; Shaofeng Yin; Ningya Feng +1 authors

WAMs Not applicable

Year 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

ParticleFormer: A 3D Point Cloud World Model for Multi-Object, Multi-Material Robotic Manipulation

Suning Huang; Qianzhong Chen; Xiaohan Zhang +2 authors

WAMs Outside quadrants

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

π₀.₅: a Vision-Language-Action Model with Open-World Generalization

Kevin Black; Noah Brown; James Darpinian +32 authors

VLA Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

DrivingGPT: Unifying Driving World Modeling and Planning with Multi-modal Autoregressive Transformers

Yuntao Chen; Yuqi Wang; Zhaoxiang Zhang

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

Mastering diverse control tasks through world models

Danijar Hafner; Jurgis Pasukonis; Jimmy Ba +1 authors

Foundational work Not applicable

Year 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

World Model-based Perception for Visual Legged Locomotion

Hang Lai; Jiahang Cao; Jiafeng Xu +5 authors

WAMs Outside quadrants

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning

Gaoyue Zhou; Hengkai Pan; Yann LeCun +1 authors

Foundational work Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

Evaluating Real-World Robot Manipulation Policies in Simulation

Xuanlin Li; Kyle Hsu; Jiayuan Gu +13 authors

Benchmarks & simulators Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

Epona: Autoregressive Diffusion World Model for Autonomous Driving

Kaiwen Zhang; Zhenyu Tang; Xiaotao Hu +9 authors

WAMs Outside quadrants

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics

Chenhao Li; Andreas Krause; Marco Hutter

WAMs Outside quadrants

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data

Ryan Punamiya; Dhruv Patel; Patcharapong Aphiwetsa +5 authors

Related resources Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model

Yupeng Zheng; Pengxuan Yang; Zebin Xing +9 authors

WAMs Outside quadrants

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

A Survey on Vision-Language-Action Models for Autonomous Driving

Sicong Jiang; Zilin Huang; Kangan Qian +17 authors

Related resources Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning

Zewei Zhou; Tianhui Cai; Seth Zhao +4 authors

VLA Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation

Yang Tian; Sizhe Yang; Jia Zeng +4 authors

Year 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

π₀: A Vision-Language-Action Flow Model for General Robot Control

Kevin Black; Noah Brown; Danny Driess +22 authors

VLA Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins

Yao Mu; Tianxing Chen; Zanxin Chen +11 authors

Benchmarks & simulators Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

FMB: A functional manipulation benchmark for generalizable robotic learning

Jianlan Luo; Charles Xu; Fangchen Liu +5 authors

Benchmarks & simulators Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

Zhuoyi Yang; Jiayan Teng; Wendi Zheng +15 authors

Components of WAMs Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

A0: An Affordance-Aware Hierarchical Model for General Robotic Manipulation

Rongtao Xu; Jian Zhang; Minghao Guo +11 authors

WAMs Outside quadrants

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

Diffusion policy: Visuomotor policy learning via action diffusion

Cheng Chi; Zhenjia Xu; Siyuan Feng +5 authors

Foundational work Not applicable

Year 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

Pseudo-Simulation for Autonomous Driving

Wei Cao; Marcel Hallgarten; Tianyu Li +11 authors

Benchmarks & simulators Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations

Yucheng Hu; Yanjiang Guo; Pengchao Wang +6 authors

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

DyWA: Dynamics-adaptive World Action Model for Generalizable Non-prehensile Manipulation

Jiangran Lyu; Ziming Li; Xuesong Shi +3 authors

Year 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

Navigation World Models

Amir Bar; Gaoyue Zhou; Danny Tran +2 authors

WAMs Outside quadrants

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

Cross-Embodiment Dexterous Manipulation through World Model Learning

Zihao He; Bo Ai; Yulin Liu +3 authors

WAMs Pending verification

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

GWM: Towards Scalable Gaussian World Models for Robotic Manipulation

Guanxing Lu; Baoxiong Jia; Puhao Li +4 authors

WAMs Outside quadrants

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

X-MOBILITY: End-To-End Generalizable Navigation via World Modeling

Wei Liu; Huihua Zhao; Chenran Li +5 authors

WAMs Outside quadrants

Year 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

OpenVLA: An Open-Source Vision-Language-Action Model

Moo Jin Kim; Karl Pertsch; Siddharth Karamcheti +14 authors

VLA Not applicable

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving

Yu Yang; Jianbiao Mei; Yukai Ma +5 authors

WAMs Outside quadrants

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

ManiGaussian++: General Robotic Bimanual Manipulation with Hierarchical Gaussian World Model

Tengbo Yu; Guanxing Lu; Zaijia Yang +7 authors

WAMs Outside quadrants

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

AgiBot-World-Contributors; Qingwen Bu; Jisong Cai +49 authors

Datasets Not applicable

Year 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

Inference-Time Enhancement of Generative Robot Policies via Predictive World Modeling

Han Qi; Haocheng Yin; Aris Zhu +2 authors

WAMs Outside quadrants

Year 2025

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

Enhancing End-to-End Autonomous Driving with Latent World Model

Yingyan Li; Lue Fan; Jiawei He +4 authors

WAMs Outside quadrants

Year 2025

Contribution summary not yet recorded.

IllustratedReading report

Doe-1: Closed-Loop Autonomous Driving with Large World Model

Wenzhao Zheng; Zetian Xia; Yuanhui Huang +3 authors

12 Dec 2024

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation

Chi-Lam Cheang; Guangzeng Chen; Ya Jing +9 authors

8 Oct 2024

Contribution summary not yet recorded.

IllustratedReading report

Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining

Jie Cheng; Ruixi Qiao; Yingwei Ma +5 authors

Foundational work

1 Oct 2024

JOWA learns an Atari world model and distributional Q-function through one shared transformer, then searches short imagined futures to choose actions. Its strongest evidence is improved aggregate game return and data-efficient offline adaptation; neither universal game-wise scaling nor unconditional planning optimality is established (e02, e03, e04, e07, e08, e11, e12).

IllustratedReading report

Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation

Homanga Bharadhwaj; Debidatta Dwibedi; Abhinav Gupta +7 authors

WAMs Outside quadrants

24 Sept 2024

Gen2Act turns a language instruction and an initial scene image into a generated human demonstration, then uses that video to condition a separate closed-loop robot policy. A pretrained VideoPoet supplies the demonstration without robot-specific fine-tuning. Auxiliary point-track prediction teaches policy representations to retain motion cues, while deployment predicts actions directly from video features and recent robot observations. Real robot results support improved generalization relative to the reported baselines, but plausible generation does not ensure correct execution, and long-horizon reliability remains limited.

IllustratedReading report

DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control

Zichen Jeff Cui; Hengkai Pan; Aadhithya Iyer +2 authors

Related resources Not applicable

18 Sept 2024

DynaMo uses action-free dynamics pretraining to make visual features useful for imitation learning. An encoder, latent inverse model and forward model jointly learn to predict next-frame embeddings; a separate policy then learns from frozen features and labeled demonstrations. Results favor DynaMo on several manipulation tasks, but include ties and initialization regressions. The contribution is a representation-learning objective, with no demonstrated use of the dynamics models for online planning.

IllustratedReading report

OccLLaMA: An Occupancy-Language-Action Generative World Model for Autonomous Driving

Julong Wei; Shanshuai Yuan; Pengfei Li +3 authors

5 Sept 2024

Contribution summary not yet recorded.

IllustratedReading report

PaliGemma: A versatile 3B VLM for transfer

Lucas Beyer; Andreas Steiner; André Susano Pinto +32 authors

Components of WAMs Not applicable

10 Jul 2024

Contribution summary not yet recorded.

IllustratedReading report

This&That: Language-Gesture Controlled Video Generation for Robot Planning

Boyang Wang; Nikhil Sridhar; Chao Feng +4 authors

WAMs Outside quadrants

8 Jul 2024

This&That turns an initial image, language and pointing coordinates into a generated video plan, then uses a separate DiVA behavior-cloning controller to follow it with live feedback. Gestures improve intent disambiguation in Bridge video generation and simulated block manipulation; real-robot execution remains untested.

IllustratedReading report

Dreamitate: Real-World Visuomotor Policy Learning via Video Generation

Junbang Liang; Ruoshi Liu; Ege Ozguroglu +5 authors

WAMs Outside quadrants

24 Jun 2024

Dreamitate learns task-specific video generation from human tool demonstrations, then extracts tool poses from synthesized stereo videos for robot execution. It outperforms the tested Diffusion Policy baseline on four physical manipulation tasks, while depending on calibrated cameras, known rigid tools, and slow open-loop generation. The central evidence concerns executed tool trajectories under specified object and scene shifts, rather than unrestricted manipulation or a general action-conditioned simulator.

IllustratedReading report

RoboDreamer: Learning Compositional World Models for Robot Imagination

Siyuan Zhou; Yilun Du; Jiaben Chen +3 authors

18 Apr 2024

RoboDreamer composes phrase-conditioned video diffusion predictions to imagine robot plans for unfamiliar instruction combinations. Optional goal images or sketches sharpen spatial specifications; a separate inverse-dynamics model converts imagined frames into actions. The strongest language-only evidence concerns human-rated video alignment, while executed success is measured separately in RLBench simulation (E03, E10–E13).

IllustratedReading report

Prediction with Action: Visual Policy Learning via Joint Denoising Process

Yanjiang Guo; Yucheng Hu; Jianke Zhang +4 authors

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking

Daniel Dauner; Marcel Hallgarten; Tianyu Li +9 authors

Benchmarks & simulators Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation

Hongtao Wu; Ya Jing; Chilam Cheang +6 authors

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

DINOv2: Learning Robust Visual Features without Supervision

Maxime Oquab; Timothée Darcet; Théo Moutakanni +23 authors

Components of WAMs Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots

Cheng Chi; Zhenjia Xu; Chuer Pan +5 authors

Datasets Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

World Models via Policy-Guided Trajectory Diffusion

Marc Rigter; Jun Yamada; Ingmar Posner

Foundational work Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving

Xiaosong Jia; Zhenjie Yang; Qifeng Li +2 authors

Benchmarks & simulators Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

Generalized Predictive Model for Autonomous Driving

Jiazhi Yang; Shenyuan Gao; Yihang Qiu +11 authors

WAMs Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

State Estimation for Robotics

Timothy D. Barfoot

Foundational work Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset

Alexander Khazatsky; Karl Pertsch; Suraj Nair +95 authors

Datasets Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

TD-MPC2: Scalable, Robust World Models for Continuous Control

Nicklas Hansen; Hao Su; Xiaolong Wang

Foundational work Not applicable

Year 2024

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning

Jianlan Luo; Zheyuan Hu; Charles Xu +7 authors

Foundational work Not applicable

Year 2024

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot Manipulation

Youpeng Wen; Junfan Lin; Yi Zhu +4 authors

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

Improved Distribution Matching Distillation for Fast Image Synthesis

Tianwei Yin; Michaël Gharbi; Taesung Park +4 authors

Foundational work Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes

Rishabh Agarwal; Nino Vieillard; Yongchao Zhou +4 authors

Foundational work Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

Revisiting Sparse Rewards for Goal-Reaching Reinforcement Learning

Gautham Vasan; Yan Wang; Fahim Shahriar +3 authors

Foundational work Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving

Wenzhao Zheng; Weiliang Chen; Yuanhui Huang +3 authors

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots

Soroush Nasiriany; Abhiram Maddukuri; Lance Zhang +5 authors

Benchmarks & simulators Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving

Xiaofeng Wang; Zheng Zhu; Guan Huang +3 authors

Year 2024

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

One-step Diffusion with Distribution Matching Distillation

Tianwei Yin; Michaël Gharbi; Richard Zhang +4 authors

Foundational work Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

Genie: Generative Interactive Environments

Jake Bruce; Michael D Dennis; Ashley Edwards +22 authors

Benchmarks & simulators Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

Diffusion for World Modeling: Visual Details Matter in Atari

Eloi Alonso; Adam Jelley; Vincent Micheli +4 authors

Foundational work Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning

Michael Matthews; Michael Beukman; Benjamin Ellis +4 authors

Benchmarks & simulators Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

Video generation models as world simulators

OpenAI

Components of WAMs Not applicable

Year 2024

Contribution summary not yet recorded.

Text noteReading report

CoPeD-Advancing Multi-Robot Collaborative Perception: A Comprehensive Dataset in Real-World Environments

Yang Zhou; Long Quang; Carlos Nieto-Granda +1 authors

Datasets Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

Octo: An Open-Source Generalist Robot Policy

Dibya Ghosh; Homer Rich Walke; Karl Pertsch +15 authors

VLA Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

Vision-Language Foundation Models as Effective Robot Imitators

Xinghang Li; Minghuan Liu; Hanbo Zhang +9 authors

VLA Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models

Siddharth Karamcheti; Suraj Nair; Ashwin Balakrishna +3 authors

Components of WAMs Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

Open X-Embodiment: Robotic Learning Datasets and RT-X Models

Open X-Embodiment Collaboration; Abby O'Neill; Abdul Rehman +291 authors

Datasets Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

ACT-Bench: Towards Action Controllable World Models for Autonomous Driving

Hidehisa Arai; Keishi Ishihara; Tsubasa Takahashi +1 authors

Benchmarks & simulators Not applicable

Year 2024

Contribution summary not yet recorded.

IllustratedReading report

Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets

Andreas Blattmann; Tim Dockhorn; Sumith Kulal +9 authors

Components of WAMs Not applicable

25 Nov 2023

Contribution summary not yet recorded.

IllustratedReading report

ADriver-I: A General World Model for Autonomous Driving

Fan Jia; Weixin Mao; Yingfei Liu +5 authors

WAMs Outside quadrants

22 Nov 2023

Contribution summary not yet recorded.

IllustratedReading report

GAIA-1: A Generative World Model for Autonomous Driving

Anthony Hu; Lloyd Russell; Hudson Yeo +5 authors

Benchmarks & simulators Not applicable

29 Sept 2023

Contribution summary not yet recorded.

IllustratedReading report

Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Jinze Bai; Shuai Bai; Shusheng Yang +6 authors

Components of WAMs Not applicable

24 Aug 2023

Contribution summary not yet recorded.

IllustratedReading report

LLaMA: Open and Efficient Foundation Language Models

Hugo Touvron; Thibaut Lavril; Gautier Izacard +11 authors

Components of WAMs Not applicable

27 Feb 2023

Contribution summary not yet recorded.

IllustratedReading report

Learning Universal Policies via Text-Guided Video Generation

Yilun Du; Mengjiao Yang; Bo Dai +5 authors

31 Jan 2023

UniPi turns a language instruction and current image into a video plan, refines its timing, then uses a separately trained inverse model to produce robot controls. Simulated manipulation results support compositional and multitask transfer. Internet pretraining improves generated real-scene plans, but its reported success is a classifier judgment on imagined final frames, not measured physical execution. [e02, e04, e06, e10, e14, e16]

IllustratedReading report

3D Gaussian Splatting for Real-Time Radiance Field Rendering

Bernhard Kerbl; Georgios Kopanas; Thomas Leimkühler +1 authors

Components of WAMs Not applicable

Year 2023

Contribution summary not yet recorded.

IllustratedReading report

PaLM-E: An Embodied Multimodal Language Model

Danny Driess; Fei Xia; Mehdi S. M. Sajjadi +19 authors

Components of WAMs Not applicable

Year 2023

Contribution summary not yet recorded.

IllustratedReading report

RT-1: Robotics Transformer for Real-World Control at Scale

Anthony Brohan; Noah Brown; Justice Carbajal +48 authors

VLA Not applicable

Year 2023

Contribution summary not yet recorded.

IllustratedReading report

DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation

Ruicheng Wang; Jialiang Zhang; Jiayi Chen +4 authors

Datasets Not applicable

Year 2023

Contribution summary not yet recorded.

IllustratedReading report

BridgeData V2: A Dataset for Robot Learning at Scale

Homer Walke; Kevin Black; Abraham Lee +11 authors

Datasets Not applicable

Year 2023

Contribution summary not yet recorded.

IllustratedReading report

DREAMWALKER: Mental Planning for Continuous Vision-Language Navigation

Hanqing Wang; Wei Liang; Luc Van Gool +1 authors

WAMs Outside quadrants

Year 2023

Contribution summary not yet recorded.

IllustratedReading report

Scalable Diffusion Models with Transformers

William Peebles; Saining Xie

Components of WAMs Not applicable

Year 2023

Contribution summary not yet recorded.

IllustratedReading report

Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

Xingchao Liu; Chengyue Gong; Qiang Liu

Foundational work Not applicable

Year 2023

Contribution summary not yet recorded.

IllustratedReading report

MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations

Ajay Mandlekar; Soroush Nasiriany; Bowen Wen +5 authors

Datasets Not applicable

Year 2023

Contribution summary not yet recorded.

IllustratedReading report

DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection

Hao Zhang; Feng Li; Shilong Liu +5 authors

Related resources Not applicable

Year 2023

Contribution summary not yet recorded.

IllustratedReading report

RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

Brianna Zitkovich; Tianhe Yu; Sichun Xu +51 authors

VLA Not applicable

Year 2023

Contribution summary not yet recorded.

IllustratedReading report

Scaling Data Generation in Vision-and-Language Navigation

Zun Wang; Jialu Li; Yicong Hong +6 authors

Datasets Not applicable

Year 2023

Contribution summary not yet recorded.

IllustratedReading report

DayDreamer: World Models for Physical Robot Learning

Philipp Wu; Alejandro Escontrela; Danijar Hafner +2 authors

Foundational work Not applicable

Year 2023

Contribution summary not yet recorded.

IllustratedReading report

Transformers are Sample-Efficient World Models

Vincent Micheli; Eloi Alonso; François Fleuret

Foundational work Not applicable

Year 2023

Contribution summary not yet recorded.

IllustratedReading report

Sigmoid Loss for Language Image Pre-Training

Xiaohua Zhai; Basil Mustafa; Alexander Kolesnikov +1 authors

Components of WAMs Not applicable

Year 2023

Contribution summary not yet recorded.

IllustratedReading report

LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning

Bo Liu; Yifeng Zhu; Chongkai Gao +4 authors

Benchmarks & simulators Not applicable

Year 2023

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

OpenScene: The Largest Up-to-Date 3D Occupancy Prediction Benchmark in Autonomous Driving

OpenScene Contributors

Datasets Not applicable

Year 2023

Contribution summary not yet recorded.

Text noteReading report

Zenseact Open Dataset: A large-scale and diverse multimodal dataset for autonomous driving

Mina Alibeigi; William Ljungbergh; Adam Tonderski +7 authors

Datasets Not applicable

Year 2023

Contribution summary not yet recorded.

IllustratedReading report

Consistency Models

Yang Song; Prafulla Dhariwal; Mark Chen +1 authors

Foundational work Not applicable

Year 2023

Contribution summary not yet recorded.

IllustratedReading report

CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks

Oier Mees; Lukás Hermann; Erick Rosete-Beas +1 authors

Benchmarks & simulators Not applicable

Year 2022

Contribution summary not yet recorded.

IllustratedReading report

Temporal Difference Learning for Model Predictive Control

Nicklas A Hansen; Hao Su; Xiaolong Wang

Foundational work Not applicable

Year 2022

Contribution summary not yet recorded.

IllustratedReading report

Rapid Exploration for Open-World Navigation with Latent Goal Models

Dhruv Shah; Benjamin Eysenbach; Nicholas Rhinehart +1 authors

Foundational work Not applicable

Year 2022

Contribution summary not yet recorded.

IllustratedReading report

LoRA: Low-Rank Adaptation of Large Language Models

Edward J. Hu; Yelong Shen; Phillip Wallis +5 authors

Foundational work Not applicable

Year 2022

Contribution summary not yet recorded.

IllustratedReading report

Ego4D: Around the World in 3,000 Hours of Egocentric Video

Kristen Grauman; Andrew Westbury; Eugene Byrne +82 authors

Datasets Not applicable

Year 2022

Contribution summary not yet recorded.

IllustratedReading report

Contrastive Learning as Goal-Conditioned Reinforcement Learning

Benjamin Eysenbach; Tianjun Zhang; Sergey Levine +1 authors

Foundational work Not applicable

Year 2022

Contribution summary not yet recorded.

IllustratedReading report

Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation

Haresh Karnan; Anirudh Nair; Xuesu Xiao +6 authors

Datasets Not applicable

Year 2022

Contribution summary not yet recorded.

IllustratedReading report

High-Resolution Image Synthesis With Latent Diffusion Models

Robin Rombach; Andreas Blattmann; Dominik Lorenz +2 authors

Components of WAMs Not applicable

Year 2022

Contribution summary not yet recorded.

IllustratedReading report

TartanDrive: A Large-Scale Dataset for Learning Off-Road Dynamics Models

Samuel Triest; Matthew Sivaprakasam; Sean J. Wang +3 authors

Datasets Not applicable

Year 2022

Contribution summary not yet recorded.

IllustratedReading report

BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View

Junjie Huang; Guan Huang; Zheng Zhu +2 authors

Components of WAMs Not applicable

22 Dec 2021

Contribution summary not yet recorded.

IllustratedReading report

BERT: A Review of Applications in Natural Language Processing and Understanding

M. V. Koroteev

Not assigned Not applicable

22 Mar 2021

Contribution summary not yet recorded.

IllustratedReading report

Mastering Atari with Discrete World Models

Danijar Hafner; Timothy Lillicrap; Mohammad Norouzi +1 authors

Foundational work Not applicable

Year 2021

Contribution summary not yet recorded.

IllustratedReading report

Pathdreamer: A World Model for Indoor Navigation

Jing Yu Koh; Honglak Lee; Yinfei Yang +2 authors

WAMs Outside quadrants

Year 2021

Contribution summary not yet recorded.

Paper Code Project

IllustratedReading report

Deep Reinforcement Learning at the Edge of the Statistical Precipice

Rishabh Agarwal; Max Schwarzer; Pablo Samuel Castro +2 authors

Evaluation metrics Not applicable

Year 2021

Contribution summary not yet recorded.

IllustratedReading report

Learning Transferable Visual Models From Natural Language Supervision

Alec Radford; Jong Wook Kim; Chris Hallacy +9 authors

Components of WAMs Not applicable

Year 2021

Contribution summary not yet recorded.

IllustratedReading report

ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations

Tongzhou Mu; Zhan Ling; Fanbo Xiang +6 authors

Benchmarks & simulators Not applicable

Year 2021

Contribution summary not yet recorded.

IllustratedReading report

NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles

Holger Caesar; Juraj Kabzan; Kok Seang Tan +6 authors

Benchmarks & simulators Not applicable

Year 2021

Contribution summary not yet recorded.

IllustratedReading report

Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments

Jacob Krantz; Erik Wijmans; Arjun Majumdar +2 authors

Benchmarks & simulators Not applicable

Year 2020

Contribution summary not yet recorded.

IllustratedReading report

Model-Based Reinforcement Learning for Atari

Lukasz Kaiser; Mohammad Babaeizadeh; Piotr Milos +11 authors

Foundational work Not applicable

Year 2020

Contribution summary not yet recorded.

IllustratedReading report

Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding

Alexander Ku; Peter Anderson; Roma Patel +2 authors

Datasets Not applicable

Year 2020

Contribution summary not yet recorded.

IllustratedReading report

nuScenes: A Multimodal Dataset for Autonomous Driving

Holger Caesar; Varun Bankiti; Alex H. Lang +7 authors

Datasets Not applicable

Year 2020

Contribution summary not yet recorded.

IllustratedReading report

RLBench: The Robot Learning Benchmark & Learning Environment

Stephen James; Zicong Ma; David Rovick Arrojo +1 authors

Benchmarks & simulators Not applicable

Year 2020

Contribution summary not yet recorded.

IllustratedReading report

Scalability in Perception for Autonomous Driving: Waymo Open Dataset

Pei Sun; Henrik Kretzschmar; Xerxes Dotiwalla +20 authors

Datasets Not applicable

Year 2020

Contribution summary not yet recorded.

IllustratedReading report

BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning

Fisher Yu; Haofeng Chen; Xin Wang +5 authors

Datasets Not applicable

Year 2020

Contribution summary not yet recorded.

IllustratedReading report

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

Colin Raffel; Noam Shazeer; Adam Roberts +6 authors

Components of WAMs Not applicable

Year 2020

Contribution summary not yet recorded.

IllustratedReading report

Leveraging Procedural Generation to Benchmark Reinforcement Learning

Karl Cobbe; Christopher Hesse; Jacob Hilton +1 authors

Benchmarks & simulators Not applicable

Year 2020

Contribution summary not yet recorded.

IllustratedReading report

Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning

Tianhe Yu; Deirdre Quillen; Zhanpeng He +4 authors

Benchmarks & simulators Not applicable

Year 2020

Contribution summary not yet recorded.

IllustratedReading report

Language Models are Few-Shot Learners

Tom Brown; Benjamin Mann; Nick Ryder +28 authors

Components of WAMs Not applicable

Year 2020

Contribution summary not yet recorded.

IllustratedReading report

Dream to Control: Learning Behaviors by Latent Imagination

Danijar Hafner; Timothy Lillicrap; Jimmy Ba +1 authors

Foundational work Not applicable

Year 2020

Contribution summary not yet recorded.

IllustratedReading report

Behaviour Suite for Reinforcement Learning

Ian Osband; Yotam Doron; Matteo Hessel +11 authors

Benchmarks & simulators Not applicable

Year 2020

Contribution summary not yet recorded.

IllustratedReading report

Learning to summarize with human feedback

Nisan Stiennon; Long Ouyang; Jeffrey Wu +6 authors

Foundational work Not applicable

Year 2020

Contribution summary not yet recorded.

IllustratedReading report

RoboNet: Large-Scale Multi-Robot Learning

Sudeep Dasari; Frederik Ebert; Stephen Tian +6 authors

Datasets Not applicable

24 Oct 2019

RoboNet pools robot experience to make visual control transferable. Pretraining improves adaptation with a few hundred target-robot trajectories, but relevant subsets can outperform the broader pool. Its central contribution is a shared dataset evaluated through two distinct control algorithms.

IllustratedReading report

A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark

Xiaohua Zhai; Joan Puigcerver; Alexander Kolesnikov +14 authors

Benchmarks & simulators Not applicable

1 Oct 2019

Contribution summary not yet recorded.

IllustratedReading report

General Evaluation for Instruction Conditioned Navigation using Dynamic Time Warping

Gabriel Ilharco; Vihan Jain; Alexander Ku +2 authors

Evaluation metrics Not applicable

11 Jul 2019

Contribution summary not yet recorded.

IllustratedReading report

When to Trust Your Model: Model-Based Policy Optimization

Michael Janner; Justin Fu; Marvin Zhang +1 authors

Foundational work Not applicable

Year 2019

Contribution summary not yet recorded.

IllustratedReading report

LIC-Fusion: LiDAR-Inertial-Camera Odometry

Xingxing Zuo; Patrick Geneva; Woosik Lee +2 authors

Related resources Not applicable

Year 2019

Contribution summary not yet recorded.

IllustratedReading report

Habitat: A Platform for Embodied AI Research

Manolis Savva; Jitendra Malik; Devi Parikh +9 authors

Benchmarks & simulators Not applicable

Year 2019

Contribution summary not yet recorded.

IllustratedReading report

Argoverse: 3D Tracking and Forecasting With Rich Maps

Ming-Fang Chang; John Lambert; Patsorn Sangkloy +8 authors

Datasets Not applicable

Year 2019

Contribution summary not yet recorded.

IllustratedReading report

Diversity is all you need: Learning skills without a reward function

Benjamin Eysenbach; Abhishek Gupta; Julian Ibarz +1 authors

Foundational work Not applicable

Year 2019

Contribution summary not yet recorded.

IllustratedReading report

HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips

Antoine Miech; Dimitri Zhukov; Jean-Baptiste Alayrac +3 authors

Datasets Not applicable

Year 2019

Contribution summary not yet recorded.

IllustratedReading report

Learning Latent Dynamics for Planning from Pixels

Danijar Hafner; Timothy Lillicrap; Ian Fischer +4 authors

Foundational work Not applicable

Year 2019

Contribution summary not yet recorded.

IllustratedReading report

Towards Accurate Generative Models of Video: A New Metric & Challenges

Thomas Unterthiner; Sjoerd van Steenkiste; Karol Kurach +3 authors

Evaluation metrics Not applicable

3 Dec 2018

Contribution summary not yet recorded.

IllustratedReading report

On Evaluation of Embodied Navigation Agents

Peter Anderson; Angel Chang; Devendra Singh Chaplot +8 authors

Evaluation metrics Not applicable

18 Jul 2018

Contribution summary not yet recorded.

IllustratedReading report

World Models

David Ha; Jürgen Schmidhuber

Foundational work Not applicable

27 Mar 2018

Contribution summary not yet recorded.

IllustratedReading report

DeepMind Control Suite

Yuval Tassa; Yotam Doron; Alistair Muldal +9 authors

Benchmarks & simulators Not applicable

2 Jan 2018

Contribution summary not yet recorded.

IllustratedReading report

Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments

Peter Anderson; Qi Wu; Damien Teney +6 authors

Datasets Not applicable

Year 2018

Contribution summary not yet recorded.

IllustratedReading report

The Unreasonable Effectiveness of Deep Features as a Perceptual Metric

Richard Zhang; Phillip Isola; Alexei A. Efros +2 authors

Evaluation metrics Not applicable

Year 2018

Contribution summary not yet recorded.

IllustratedReading report

Sim-to-Real Transfer of Robotic Control with Dynamics Randomization

Xue Bin Peng; Marcin Andrychowicz; Wojciech Zaremba +1 authors

Foundational work Not applicable

Year 2018

Contribution summary not yet recorded.

IllustratedReading report

The Kinetics Human Action Video Dataset

Will Kay; Joao Carreira; Karen Simonyan +9 authors

Datasets Not applicable

19 May 2017

Contribution summary not yet recorded.

IllustratedReading report

Matterport3D: Learning from RGB-D Data in Indoor Environments

Angel X. Chang; Angela Dai; Thomas A. Funkhouser +6 authors

Datasets Not applicable

Year 2017

Contribution summary not yet recorded.

IllustratedReading report

Factor Graphs for Robot Perception

Frank Dellaert; Michael Kaess

Foundational work Not applicable

Year 2017

Contribution summary not yet recorded.

IllustratedReading report

Neural Discrete Representation Learning

Aaron van den Oord; Oriol Vinyals; Koray Kavukcuoglu

Components of WAMs Not applicable

Year 2017

Contribution summary not yet recorded.

IllustratedReading report

The "Something Something" Video Database for Learning and Evaluating Visual Common Sense

Raghav Goyal; Samira Ebrahimi Kahou; Vincent Michalski +11 authors

Datasets Not applicable

Year 2017

Contribution summary not yet recorded.

IllustratedReading report

GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

Martin Heusel; Hubert Ramsauer; Thomas Unterthiner +2 authors

Evaluation metrics Not applicable

Year 2017

Contribution summary not yet recorded.

IllustratedReading report

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

Charles R. Qi; Hao Su; Kaichun Mo +1 authors

Components of WAMs Not applicable

Year 2017

Contribution summary not yet recorded.

IllustratedReading report

CARLA: An Open Urban Driving Simulator

Alexey Dosovitskiy; Germán Ros; Felipe Codevilla +2 authors

Benchmarks & simulators Not applicable

Year 2017

Contribution summary not yet recorded.

IllustratedReading report

Deep Reinforcement Learning from Human Preferences

Paul F. Christiano; Jan Leike; Tom Brown +3 authors

Foundational work Not applicable

Year 2017

Contribution summary not yet recorded.

IllustratedReading report

CIDEr: Consensus-Based Image Description Evaluation

Ramakrishna Vedantam; C. Lawrence Zitnick; Devi Parikh

Evaluation metrics Not applicable

Year 2015

Contribution summary not yet recorded.

IllustratedReading report

Advances and applications of occupancy models

Larissa L Bailey; Darryl I MacKenzie; James D Nichols

Not assigned Not applicable

Year 2014

Contribution summary not yet recorded.

Text noteReading report

Auto-Encoding Variational Bayes

Diederik P Kingma; Max Welling

Components of WAMs Not applicable

Year 2014

Contribution summary not yet recorded.

IllustratedReading report

The Arcade Learning Environment: An Evaluation Platform for General Agents

Marc G. Bellemare; Yavar Naddaf; Joel Veness +1 authors

Benchmarks & simulators Not applicable

Year 2013

Contribution summary not yet recorded.

IllustratedReading report

A benchmark for the evaluation of RGB-D SLAM systems

Jrgen Sturm; Nikolas Engelhard; Felix Endres +2 authors

Datasets Not applicable

Year 2012

Contribution summary not yet recorded.

IllustratedReading report

Are we ready for autonomous driving? The KITTI vision benchmark suite

Andreas Geiger; Philip Lenz; Raquel Urtasun

Datasets Not applicable

Year 2012

Contribution summary not yet recorded.

IllustratedReading report

Monte-Carlo Planning in Large POMDPs

David Silver; Joel Veness

Foundational work Not applicable

Year 2010

Contribution summary not yet recorded.

IllustratedReading report

METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments

Satanjeev Banerjee; Alon Lavie

Evaluation metrics Not applicable

Year 2005

Contribution summary not yet recorded.

IllustratedReading report

Probabilistic Robotics

Sebastian Thrun; Wolfram Burgard; Dieter Fox

Foundational work Not applicable

Year 2005

Contribution summary not yet recorded.

IllustratedReading report

Image Quality Assessment: From Error Visibility to Structural Similarity

Zhou Wang; Alan C. Bovik; Hamid R. Sheikh +1 authors

Evaluation metrics Not applicable

Year 2004

Contribution summary not yet recorded.

IllustratedReading report

ROUGE: A Package for Automatic Evaluation of Summaries

Chin-Yew Lin

Evaluation metrics Not applicable

Year 2004

Contribution summary not yet recorded.

IllustratedReading report

Real-time humanoid motion generation through ZMP manipulation based on inverted pendulum control

Tomomichi Sugihara; Yoshihiko Nakamura; Hirochika Inoue

Foundational work Not applicable

Year 2002

Contribution summary not yet recorded.

IllustratedReading report

Bleu: a Method for Automatic Evaluation of Machine Translation

Kishore Papineni; Salim Roukos; Todd Ward +1 authors

Evaluation metrics Not applicable

Year 2002

Contribution summary not yet recorded.

IllustratedReading report

Planning and acting in partially observable stochastic domains

Leslie Pack Kaelbling; Michael L. Littman; Anthony R. Cassandra

Foundational work Not applicable

Year 1998

Contribution summary not yet recorded.

IllustratedReading report

Reinforcement Learning: An Introduction

Richard S. Sutton; Andrew G. Barto

Foundational work Not applicable

Year 1998

Contribution summary not yet recorded.

Text noteReading report

Model predictive control: Theory and practice—A survey

Carlos E. García; David M. Prett; Manfred Morari

Foundational work Not applicable

Year 1989

Contribution summary not yet recorded.

Text noteReading report

Advancing AI for the physical world

Microsoft Research

VLA Not applicable

Date not recorded

Contribution summary not yet recorded.

Text noteReading report

Missing a paper, or found a correction?

Suggest an update on GitHub ↗