PhysAlign: A Benchmark for Evidence-Grounded Role Alignment in Multimodal Physics Reasoning
cs.AI
Submitted: 2026-09-27
Updated: 2026-09-27
Code: https://github.com/HCPLab-SYSU/PhysAlign
Terminology
Sources
- SeePhys Pro: Diagnosing Modality Transfer and Blind-Training Effects in Multimodal RLVR for Physics Reasoning
- PhysUniBench: A Multi-Modal Physics Reasoning Benchmark at Undergraduate Level
- VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations
- LiveK12Bench: Have Large Multimodal Models Truly Conquered High School-level Examinations?
- PhysElite: How Far Are LLMs from Solving Olympiad-Level Physics Problems?
- PhyX: Does Your Model Have the "Wits" for Physical Reasoning?
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- Towards VQA Models That Can Read
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection