Safety
MindWorldBench: Evaluating Mental-State-to-Behavior Reasoning in Image-to-Video Generation
arXiv:2609.39147v1 Announce Type: new Abstract: Current image-to-video models achieve visual realism and physical plausibility, but reasoning about mental states remains unexplored. Actions are driven
arXiv:2609.39147v1 Announce Type: new Abstract: Current image-to-video models achieve visual realism and physical plausibility, but reasoning about mental states remains unexplored. Actions are driven by belief, desire, and perception, requiring inference beyond explicit instructions. We introduce MindWorldBench to evaluate mental-state-conditioned video generation. We formalize this as mental-state-to-behavior reasoning, where models generate actions from a world state and latent variables without explicit action prompts. MindWorldBench utilizes Zero-Action Prompting and a counterfactual design with 744 prompts to isolate the causal effects of mental states. An automated pipeline evaluates video quality, commonsense plausibility, and mental-state consistency. Evaluations of 11 models show that despite visual fidelity and physical reasoning, models fail to align behaviors with latent mental states. We identify a failure mode, termed Omniscient Bias, where models default to the objective world state rather than human's subjective belief. These results demonstrate a disconnect between visual generation and cognitive reasoning, suggesting a need for explicit mental-state modeling in video generation systems. Project website: https://richard2049-lee.github.io/MindWorldBench/
Related
- Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model
- Beyond Shortcuts: Mitigating Visual Illusions in Frozen VLMs via Qualitative Reasoning
- SIFT: Self-Imagination Fine-Tuning for Physically Plausible Motion in Video Diffusion Models
- TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL
Source: arXiv cs.CV | 2026-10-01