Latent-WAM++: Shaping World and Action Representations for End-to-End Autonomous Driving
cs.CV
Submitted: 2026-11-07
Updated: 2026-11-07
Terminology
Sources
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- Improved Mean Flows: On the Challenges of Fastforward Generative Models
- DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving
- Generalized Trajectory Scoring for End-to-end Multimodal Planning
- One-step Latent-free Image Generation with Pixel Mean Flows
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- MeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving
- Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving
- Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving
- DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving
- Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs