Mimicking the Physicist's Eye:A VLM-centric Approach for Physics Formula Discovery
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909751055482880 |
|---|---|
| author | Liu, Jiaqi Lai, Songning Li, Pengze Yu, Di Zhou, Wenjie Zhou, Yiyang Xia, Peng Wang, Zijun Chen, Xi Tang, Shixiang Bai, Lei Ouyang, Wanli Ding, Mingyu Yao, Huaxiu Wang, Aoran |
| author_facet | Liu, Jiaqi Lai, Songning Li, Pengze Yu, Di Zhou, Wenjie Zhou, Yiyang Xia, Peng Wang, Zijun Chen, Xi Tang, Shixiang Bai, Lei Ouyang, Wanli Ding, Mingyu Yao, Huaxiu Wang, Aoran |
| contents | Automated discovery of physical laws from observational data in the real world is a grand challenge in AI. Current methods, relying on symbolic regression or LLMs, are limited to uni-modal data and overlook the rich, visual phenomenological representations of motion that are indispensable to physicists. This "sensory deprivation" severely weakens their ability to interpret the inherent spatio-temporal patterns within dynamic phenomena. To address this gap, we propose VIPER-R1, a multimodal model that performs Visual Induction for Physics-based Equation Reasoning to discover fundamental symbolic formulas. It integrates visual perception, trajectory data, and symbolic reasoning to emulate the scientific discovery process. The model is trained via a curriculum of Motion Structure Induction (MSI), using supervised fine-tuning to interpret kinematic phase portraits and to construct hypotheses guided by a Causal Chain of Thought (C-CoT), followed by Reward-Guided Symbolic Calibration (RGSC) to refine the formula structure with reinforcement learning. During inference, the trained VIPER-R1 acts as an agent: it first posits a high-confidence symbolic ansatz, then proactively invokes an external symbolic regression tool to perform Symbolic Residual Realignment (SR^2). This final step, analogous to a physicist's perturbation analysis, reconciles the theoretical model with empirical data. To support this research, we introduce PhysSymbol, a new 5,000-instance multimodal corpus. Experiments show that VIPER-R1 consistently outperforms state-of-the-art VLM baselines in accuracy and interpretability, enabling more precise discovery of physical laws. Project page: https://jiaaqiliu.github.io/VIPER-R1/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_17380 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mimicking the Physicist's Eye:A VLM-centric Approach for Physics Formula Discovery Liu, Jiaqi Lai, Songning Li, Pengze Yu, Di Zhou, Wenjie Zhou, Yiyang Xia, Peng Wang, Zijun Chen, Xi Tang, Shixiang Bai, Lei Ouyang, Wanli Ding, Mingyu Yao, Huaxiu Wang, Aoran Artificial Intelligence Automated discovery of physical laws from observational data in the real world is a grand challenge in AI. Current methods, relying on symbolic regression or LLMs, are limited to uni-modal data and overlook the rich, visual phenomenological representations of motion that are indispensable to physicists. This "sensory deprivation" severely weakens their ability to interpret the inherent spatio-temporal patterns within dynamic phenomena. To address this gap, we propose VIPER-R1, a multimodal model that performs Visual Induction for Physics-based Equation Reasoning to discover fundamental symbolic formulas. It integrates visual perception, trajectory data, and symbolic reasoning to emulate the scientific discovery process. The model is trained via a curriculum of Motion Structure Induction (MSI), using supervised fine-tuning to interpret kinematic phase portraits and to construct hypotheses guided by a Causal Chain of Thought (C-CoT), followed by Reward-Guided Symbolic Calibration (RGSC) to refine the formula structure with reinforcement learning. During inference, the trained VIPER-R1 acts as an agent: it first posits a high-confidence symbolic ansatz, then proactively invokes an external symbolic regression tool to perform Symbolic Residual Realignment (SR^2). This final step, analogous to a physicist's perturbation analysis, reconciles the theoretical model with empirical data. To support this research, we introduce PhysSymbol, a new 5,000-instance multimodal corpus. Experiments show that VIPER-R1 consistently outperforms state-of-the-art VLM baselines in accuracy and interpretability, enabling more precise discovery of physical laws. Project page: https://jiaaqiliu.github.io/VIPER-R1/ |
| title | Mimicking the Physicist's Eye:A VLM-centric Approach for Physics Formula Discovery |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2508.17380 |