Breaking survivorship bias in driving world models
cs.RO
Submitted: 2026-11-08
Updated: 2026-11-08
Code: https://github.com/OpenDriveLab/Vista
Project page: https://zihaosheng.github.io/NWM
Terminology
Sources
- Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models
- X-World: Controllable Ego-Centric Multi-Camera World Models for Scalable End-to-End Driving
- Ctrl-Crash: Controllable Diffusion for Realistic Car Crashes
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- Towards Accurate Generative Models of Video: A New Metric & Challenges
- YOLOv11: An Overview of the Key Architectural Enhancements
- Revisiting Feature Prediction for Learning Visual Representations from Video
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