PhySimCode: A Benchmark and Evaluation Method for Physics Video to Code Generation
cs.CV
Submitted: 2026-10-11
Updated: 2026-10-11
Comments: 34 pages, 8 figures, 20 tables. Project page: https://sourajakundu.github.io/PhySimCode/
Code: https://github.com/SourajaKundu/PhySimCode
Project page: https://sourajakundu.github.io/PhySimCode
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Cosmos World Foundation Model Platform for Physical AI
- Physion: Evaluating Physical Prediction from Vision in Humans and Machines
- Visual Physics: Discovering Physical Laws from Videos
- ComPhy: Compositional Physical Reasoning of Objects and Events from Videos
- Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation
- DiffTaichi: Differentiable Programming for Physical Simulation
- Physics-as-Inverse-Graphics: Unsupervised Physical Parameter Estimation from Video
- PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification
- Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning
- Solving Physics Olympiad via Reinforcement Learning on Physics Simulators
- IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning
- MM-ReCoder: Advancing Chart-to-Code Generation with Reinforcement Learning and Self-Correction
- Wan: Open and Advanced Large-Scale Video Generative Models
- Training and Benchmarking Code Generation for Physics-Inspired Animations
- PhysCodeBench: Benchmarking Physics-Aware Symbolic Simulation of 3D Scenes via Self-Corrective Multi-Agent Refinement
- CLEVRER: CoLlision Events for Video REpresentation and Reasoning
- VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning
- ContPhy: Continuum Physical Concept Learning and Reasoning from Videos
- PhysInOne: Visual Physics Learning and Reasoning in One Suite
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models