Reinforcing End-to-End Autonomous Driving Safety via Negative-Aware Planning in a Unified World-Action Model
cs.RO, cs.CV
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/Zizizihao/NegWAM
Terminology
Sources
- Post-Training in End-to-End Autonomous Driving
- EponaV2: Driving World Model with Comprehensive Future Reasoning
- World Engine: Towards the Era of Post-Training for Autonomous Driving
- DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving
- Test-Time Trajectory Optimization for Autonomous Driving
- Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives
- Learning from Mistakes: Post-Training for Driving VLA with Takeover Data
- Do Better Visual Representations Always Lead to Better End-to-End Autonomous Driving?
- Causal World Modeling for Robot Control
- 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
- DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning
- Wan: Open and Advanced Large-Scale Video Generative Models
- Generalized Trajectory Scoring for End-to-end Multimodal Planning
- SpanVLA: Learning from Negative-Recovery Samples with Fast Action Bridging for Vision-Language-Action Model
- DriveFuture: Future-Aware Latent World Models for Autonomous Driving
- Hydra-MDP++: Advancing End-to-End Driving via Expert-Guided Hydra-Distillation
- DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving
- DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Driving
- Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation