TRAVL：让视频语言模型成为更好的物理不合理性评判者的配方
TRAVL: A Recipe for Making Video-Language Models Better Judges of Physics Implausibility
AI总结：
本文提出TRAVL微调配方和ImplausiBench基准，通过轨迹感知注意力模块和平衡数据集训练视频语言模型，以提升其物理不合理性检测能力，并实现更严格的物理推理评估。
摘要：
尽管现代视频生成模型具有令人印象深刻的视觉保真度，但它们经常生成违反直觉物理规律的序列，例如物体漂浮、瞬移或以违背因果性的方式变形。虽然人类可以轻易察觉此类不合理性，但目前仍缺乏一种稳健的方法来定量评估视频中的物理真实性。在这项工作中，我们探讨了视频语言模型（VLM）能否被训练成可靠的物理合理性评判者。我们发现，现有的VLM难以识别物理违规，这暴露了它们在时间与因果推理方面的根本局限性。为解决这一问题，我们提出了TRAVL，一种微调配方，它结合了平衡的训练数据集与轨迹感知注意力模块，以改善VLM中的运动编码与判别能力。为了更严格地评估物理推理，我们提出了ImplausiBench，一个包含300个视频（150个真实，150个生成）的基准，该基准消除了语言偏差并隔离了视觉-时间理解。性能评估同时采用金标准人类判断和更严格的LLM作为评判者的指标。TRAVL与ImplausiBench共同提供了一个统一的框架，用于探测和改善多模态模型中的物理合理性，揭示视觉-时间理解中一个具有挑战性且未被充分探索的方面。
英文摘要：
Despite impressive visual fidelity, modern video generative models frequently produce sequences that violate intuitive physical laws, such as objects floating, teleporting, or morphing in ways that defy causality. While humans can easily detect such implausibilities, there remains no robust method for quantitatively assessing physical realism in video. In this work, we explore whether Video-Language Models (VLMs) can be trained to serve as reliable judges of physical plausibility. We find that existing VLMs struggle to identify physics violations, exposing fundamental limitations in their temporal and causal reasoning. To address this, we introduce TRAVL, a fine-tuning recipe that combines a balanced training dataset with a trajectory-aware attention module to improve motion encoding and discrimination in VLMs. To evaluate physical reasoning more rigorously, we propose ImplausiBench, a benchmark of 300 videos (150 real, 150 generated) that removes linguistic biases and isolates visual-temporal understanding. Performance is reported both with gold-standard human judgments and stricter LLM-as-judge metrics. Together, TRAVL and ImplausiBench offer a unified framework for probing and improving physical plausibility in multimodal models, shedding light on a challenging and underexplored aspect of visual-temporal understanding.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
