Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.16007 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915747584802816 |
|---|---|
| author | Mak, Chak-Wing Zhu, Guanyu Zhang, Boyi Li, Hongji Chi, Xiaowei Zhang, Kevin Wu, Yichen He, Yangfan Fan, Chun-Kai Lu, Wentao Ge, Kuangzhi Fang, Xinyu He, Hongyang Lu, Kuan Xu, Tianxiang Zhang, Li Ni, Yongxin Li, Youhua Zhang, Shanghang |
| author_facet | Mak, Chak-Wing Zhu, Guanyu Zhang, Boyi Li, Hongji Chi, Xiaowei Zhang, Kevin Wu, Yichen He, Yangfan Fan, Chun-Kai Lu, Wentao Ge, Kuangzhi Fang, Xinyu He, Hongyang Lu, Kuan Xu, Tianxiang Zhang, Li Ni, Yongxin Li, Youhua Zhang, Shanghang |
| contents | Modern foundational Multimodal Large Language Models (MLLMs) and video world models have advanced significantly in mathematical, common-sense, and visual reasoning, but their grasp of the underlying physics remains underexplored. Existing benchmarks attempting to measure this matter rely on synthetic, Visual Question Answer templates or focus on perceptual video quality that is tangential to measuring how well the video abides by physical laws. To address this fragmentation, we introduce PhysicsMind, a unified benchmark with both real and simulation environments that evaluates law-consistent reasoning and generation over three canonical principles: Center of Mass, Lever Equilibrium, and Newton's First Law. PhysicsMind comprises two main tasks: i) VQA tasks, testing whether models can reason and determine physical quantities and values from images or short videos, and ii) Video Generation(VG) tasks, evaluating if predicted motion trajectories obey the same center-of-mass, torque, and inertial constraints as the ground truth. A broad range of recent models and video generation models is evaluated on PhysicsMind and found to rely on appearance heuristics while often violating basic mechanics. These gaps indicate that current scaling and training are still insufficient for robust physical understanding, underscoring PhysicsMind as a focused testbed for physics-aware multimodal models. Our data will be released upon acceptance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_16007 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PhysicsMind: Sim and Real Mechanics Benchmarking for Physical Reasoning and Prediction in Foundational VLMs and World Models Mak, Chak-Wing Zhu, Guanyu Zhang, Boyi Li, Hongji Chi, Xiaowei Zhang, Kevin Wu, Yichen He, Yangfan Fan, Chun-Kai Lu, Wentao Ge, Kuangzhi Fang, Xinyu He, Hongyang Lu, Kuan Xu, Tianxiang Zhang, Li Ni, Yongxin Li, Youhua Zhang, Shanghang Computer Vision and Pattern Recognition Artificial Intelligence Modern foundational Multimodal Large Language Models (MLLMs) and video world models have advanced significantly in mathematical, common-sense, and visual reasoning, but their grasp of the underlying physics remains underexplored. Existing benchmarks attempting to measure this matter rely on synthetic, Visual Question Answer templates or focus on perceptual video quality that is tangential to measuring how well the video abides by physical laws. To address this fragmentation, we introduce PhysicsMind, a unified benchmark with both real and simulation environments that evaluates law-consistent reasoning and generation over three canonical principles: Center of Mass, Lever Equilibrium, and Newton's First Law. PhysicsMind comprises two main tasks: i) VQA tasks, testing whether models can reason and determine physical quantities and values from images or short videos, and ii) Video Generation(VG) tasks, evaluating if predicted motion trajectories obey the same center-of-mass, torque, and inertial constraints as the ground truth. A broad range of recent models and video generation models is evaluated on PhysicsMind and found to rely on appearance heuristics while often violating basic mechanics. These gaps indicate that current scaling and training are still insufficient for robust physical understanding, underscoring PhysicsMind as a focused testbed for physics-aware multimodal models. Our data will be released upon acceptance. |
| title | PhysicsMind: Sim and Real Mechanics Benchmarking for Physical Reasoning and Prediction in Foundational VLMs and World Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2601.16007 |