MindWorldBench：评估图像到视频生成中的心理状态到行为推理
MindWorldBench: Evaluating Mental-State-to-Behavior Reasoning in Image-to-Video Generation
浏览论文内容
中文总结 AI 辅助
MindWorldBench通过反事实设计和744个提示评估图像到视频模型的心理状态到行为推理，发现11个模型存在全知偏差，未能将行为与潜在心理状态对齐，揭示了视觉生成与认知推理的脱节。
中文摘要 AI 辅助
当前的图像到视频模型实现了视觉真实感和物理合理性，但对心理状态的推理仍未得到探索。行为由信念、欲望和感知驱动，需要超越显式指令的推理。我们引入MindWorldBench来评估心理状态条件下的视频生成。我们将其形式化为心理状态到行为推理，即模型从世界状态和潜在变量生成行为，而无需显式行为提示。MindWorldBench利用零行为提示和反事实设计，包含744个提示，以隔离心理状态的因果效应。一个自动化流程评估视频质量、常识合理性和心理状态一致性。对11个模型的评估显示，尽管视觉保真度和物理推理表现良好，模型仍未能使行为与潜在心理状态对齐。我们识别出一种失败模式，称为全知偏差，即模型默认采用客观世界状态而非人类的主观信念。这些结果表明视觉生成与认知推理之间存在脱节，提示视频生成系统需要显式的心理状态建模。项目网站：此https URL
英文摘要
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/
发表机构
- Peking University（北京大学）
- University of Science and Technology Beijing（北京科技大学）
- City University of Hong Kong（香港城市大学）
- Nanyang Technological University（南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。
