ContPhy：从视频中学习与推理连续体物理概念
ContPhy: Continuum Physical Concept Learning and Reasoning from Videos
AI总结：
本文提出连续体物理数据集ContPhy，评估AI在质量、密度等物理属性推断及动力学预测上的物理常识，并引入结合粒子物理模型与大语言模型的ContPRO模型，实现精确预测与可解释推理。
摘要：
我们引入了连续体物理数据集（ContPhy），这是一种用于评估机器物理常识的新颖基准。ContPhy 通过涵盖在各种场景中对质量、密度等不同物理属性的推断，并预测相应的动力学，从而补充了现有的物理推理基准。我们评估了一系列 AI 模型，发现它们在 ContPhy 上仍难以取得令人满意的表现，这表明当前 AI 模型仍然缺乏针对连续体（尤其是软体）的物理常识，并说明了所提出数据集的价值。我们还引入了一个预言机模型（ContPRO），它将基于粒子的物理动力学模型与近期的大语言模型相结合，兼具两者的优势：精确的动力学预测和可解释的推理。ContPhy 旨在推动在多样化物理场景中的感知与推理进展，缩小人类与机器在理解物理世界方面的智能鸿沟。项目页面：https://physical-reasoning-project.github.io
英文摘要：
We introduce the Continuum Physical Dataset (ContPhy), a novel benchmark for assessing machine physical commonsense. ContPhy complements existing physical reasoning benchmarks by encompassing the inference of diverse physical properties, such as mass and density, across various scenarios and predicting corresponding dynamics. We evaluated a range of AI models and found that they still struggle to achieve satisfactory performance on ContPhy, which shows that the current AI models still lack physical commonsense for the continuum, especially soft-bodies, and illustrates the value of the proposed dataset. We also introduce an oracle model (ContPRO) that marries the particle-based physical dynamic models with the recent large language models, which enjoy the advantages of both models, precise dynamic predictions, and interpretable reasoning. ContPhy aims to spur progress in perception and reasoning within diverse physical settings, narrowing the divide between human and machine intelligence in understanding the physical world. Project page: https://physical-reasoning-project.github.io
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。
