Drive-HWM: Hierarchical World Models for Dynamic-Latent Guided Autonomous Driving
Classification
View four quadrants- Major category
- WAMs
- Quadrant
- Not assigned
- Architecture
- Not assigned
- Prediction paradigm
- Not assigned
- Subcategories
- Autonomous drivingLatent prediction & JEPA
- Source review status
- Not assigned
Category review. A slow future-motion predictor provides dynamic latents to an observation-grounded driving action model; predictive latents remain active in action generation at deployment. Reading evidence
Contribution
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.
Abstract
An abstract has not been added yet.
Affiliations
School of Artificial Intelligence, Beihang University, Beijing, China; Shanghai Jiao Tong University, Shanghai, China; Dim12 AI; GigaAI; National University of Singapore, Singapore; TeleAI