WorldEval: World Model as Real-World Robot Policies Evaluator
Classification
View four quadrants- Major category
- Benchmarks & simulators
- Quadrant
- Not applicable
- Architecture
- Not applicable
- Prediction paradigm
- Not applicable
- Source review status
- Not assigned
Category review. Policy embeddings condition a separately adapted video simulator, and a verifier judges generated outcomes to estimate policy rankings against real trials. The system evaluates policies rather than producing their executable actions. The cataloged contribution is a dataset/data-generation method or evaluation/simulation resource, not the architecture of an evaluated or external policy. Reading evidence
Contribution
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.
Abstract
An abstract has not been added yet.
Affiliations
Midea Group; East China Normal University