Hallucination in World Models is Predictable and Preventable
- Published
- Source
- arXiv
- Paper number
- 507
- Field
- Machine Learning
- arXiv ID
- 2606.27326
Key points
- It defines three types of hallucination: perceptual hallucination from the tokenizer, action hallucination from marginalization in the dynamics, and scene hallucination from rollout divergence.
- MMBench2 contains 65,600 trajectories spanning 427 hours, 210 tasks, and 10 domains, together with ground-truth actions, rewards, and the simulator.
- Coverage-aware training improves both the tokenizer and dynamics, which raises rollout PSNR by 0.88 dB.
- Collecting only 50 curiosity-driven trajectories yields 0.325 adaptation performance on unseen tasks, which is about 90 percent of the expert or human score of 0.362.
- The hallucination predictors show a strong negative Spearman correlation of about 0.80 with rollout ΔPSNR.
- The analysis also compares an off-the-shelf tokenizer, Wan 2.1 VAE, with an in-domain tokenizer.
Paper links
External research summaries. These are not HDATF publications or measured product results.