Breaking survivorship bias in driving world models
- Published
- Source
- arXiv
- Paper number
- 1448
- Field
- Computer Vision
- arXiv ID
- 2611.11516
Key points
- At only 0.5 s before collision, Vista and GEM imagined the collision in 9% and 12% of the scenes, respectively, whereas the NWM reached 86%.
- On routine MM-AU clips, the NWM imagined a collision in only 8% of the futures, showing it did not simply associate accident-footage appearance with collisions.
- On 200 challenging NAVSIM scenes, NWM-guided selection achieved a PDMS of 0.783 against 0.637 for Vista-guided selection, approaching the oracle 0.959.
- In real-vehicle pedestrian-dummy trials, the NWM chose braking correctly at all decision frames in the Response stage while Vista’s accuracy fell to 30%.
- The dominant failure modes of both baselines were rewriting the future to avoid the collision, such as making the agent vanish or freezing the scene.
Paper links
External research summaries. These are not HDATF publications or measured product results.