USC-GVL / PhysBenchLinks
[ICLR 2025] Official implementation and benchmark evaluation repository of <PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding>
☆75Updated 5 months ago
Alternatives and similar repositories for PhysBench
Users that are interested in PhysBench are comparing it to the libraries listed below
Sorting:
- ☆98Updated 2 weeks ago
- ☆103Updated 3 months ago
- [NeurIPS 2025] Source codes for the paper "MindJourney: Test-Time Scaling with World Models for Spatial Reasoning"☆93Updated last week
- ☆21Updated last year
- SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worlds☆73Updated last week
- ☆41Updated 5 months ago
- Official repository for "RLVR-World: Training World Models with Reinforcement Learning" (NeurIPS 2025), https://arxiv.org/abs/2505.13934☆132Updated 2 weeks ago
- MetaSpatial leverages reinforcement learning to enhance 3D spatial reasoning in vision-language models (VLMs), enabling more structured, …☆193Updated 6 months ago
- [ICLR 2025 Spotlight] Grounding Video Models to Actions through Goal Conditioned Exploration☆58Updated 6 months ago
- ☆150Updated 10 months ago
- [CVPR 2024] Situational Awareness Matters in 3D Vision Language Reasoning☆42Updated 11 months ago
- Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give…☆178Updated last month
- Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (arXiv 2025)☆190Updated 3 months ago
- Official implementation of "Self-Improving Video Generation"☆75Updated 6 months ago
- ☆84Updated last year
- OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models☆71Updated last month
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆173Updated 4 months ago
- Official Repo of From Masks to Worlds: A Hitchhiker’s Guide to World Models.☆48Updated 3 weeks ago
- VLA-RFT: Vision-Language-Action Models with Reinforcement Fine-Tuning☆81Updated last month
- Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces☆85Updated 5 months ago
- Multi-SpatialMLLM Multi-Frame Spatial Understanding with Multi-Modal Large Language Models☆158Updated last month
- [CVPR'24 Highlight] The official code and data for paper "EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Lan…☆62Updated 7 months ago
- ☆37Updated 2 months ago
- Code for Stable Control Representations☆26Updated 7 months ago
- A paper list for spatial reasoning☆160Updated last week
- [NeurIPS 2024] Official Repository of Multi-Object Hallucination in Vision-Language Models☆32Updated last year
- [NeurIPS 2025] OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding☆67Updated last month
- [Nips 2025] EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation☆122Updated 3 months ago
- ☆30Updated 11 months ago
- Official repository for "iVideoGPT: Interactive VideoGPTs are Scalable World Models" (NeurIPS 2024), https://arxiv.org/abs/2405.15223☆156Updated last month