HumanPhys: A Human-Centric Physical-World Perception Benchmark for Real-World Visual Reasoning
cs.CV
Submitted: 2026-10-10
Updated: 2026-10-10
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion
- SpatialBot: Precise Spatial Understanding with Vision Language Models
- SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities
- SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models
- Detecting Attended Visual Targets in Video
- SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
- S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Kimi-VL Technical Report
- EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models
- FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding
- BLINK: Multimodal Large Language Models Can See but Not Perceive
- Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
- HumanMoveVQA: Can Video MLLMs reason about human movement in videos?
- GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
- GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
- SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments
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