# PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs

arXiv: https://arxiv.org/abs/2608.02150 · HTML: https://mlsanity.com/paper/2608.02150/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 20 of its 32 references that are in the map.
- First posted on arXiv 3 Aug 2026.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)

## Builds on (most cited first, 20 of 20)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [3D-VLA: A 3D Vision-Language-Action Generative World Model](https://mlsanity.com/paper/2403.09631/) (2024)
- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [VideoPhy: Evaluating Physical Commonsense for Video Generation](https://mlsanity.com/paper/2406.03520/) (2024)
- [Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation](https://mlsanity.com/paper/2410.05363/) (2024)
- [VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation](https://mlsanity.com/paper/2503.06800/) (2025)
- [MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting](https://mlsanity.com/paper/2403.03174/) (2024)
- [LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning](https://mlsanity.com/paper/2406.11815/) (2024)
- [UniVideo: Unified Understanding, Generation, and Editing for Videos](https://mlsanity.com/paper/2510.08377/) (2025)
- [LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence](https://mlsanity.com/paper/2605.25979/) (2026)
- [A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs](https://mlsanity.com/paper/2506.09987/) (2025)
- [Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning](https://mlsanity.com/paper/2512.15693/) (2025)
- [PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos](https://mlsanity.com/paper/2412.01800/) (2024)
- [PhyGrasp: Generalizing Robotic Grasping with Physics-informed Large Multimodal Models](https://mlsanity.com/paper/2402.16836/) (2024)
- [MVPBench: A Multi-Video Perception Evaluation Benchmark for Multi-Modal Video Understanding](https://mlsanity.com/paper/2603.22756/) (2026)

## Abstract (arXiv)

Embodied intelligence and world models require video understanding systems to go beyond recognizing objects and actions and develop an understanding of physical regularities. However, despite their strong performance on general video understanding tasks, current video-language models still struggle to reliably determine whether an observed event conforms to specific physical laws. Existing benchmarks primarily assess the physical quality of generated videos, providing limited support for systematically evaluating and improving the physical-law understanding of Video Large Language Models (VideoLLMs). To address this gap, we introduce PhyCheck, a video question answering dataset organized at two complementary levels of granularity. The coarse-grained subset asks models to determine whether the phenomenon shown in a video conforms to or violates physical laws, while the fine-grained subset further examines whether models can capture physical details responsible for the violation or compliance. We use these subsets as structured supervision to improve physical understanding. In addition, the dataset contains a diagnostic subset with external causal context that reveal hidden factors affecting physical plausibility, assessing whether models can recalibrate their judgments accordingly. Experiments with Fine-tune Qwen2.5-VL show that training with the proposed data substantially improves the understanding of physical-consistency, while evaluations in the diagnostic subset reveal that current models still have difficulty incorporating additional causal conditions into their decisions. These findings highlight the gap between recognizing surface-level inconsistencies and understanding underlying physical mechanisms, and provide a foundation for evaluating and improving physical understanding in Video-LLMs.