Tag
This paper audits multimodal physics evaluation pipelines, revealing issues like train-eval contamination, translation drift, and MCQ saturation. It releases new datasets (PhysCorp-A, PhysR1Corp, PhysOlym-A) and a training recipe (Physics-R1) that significantly improves performance on held-out olympiad problems.
The paper introduces SeePhys Pro, a benchmark to diagnose modality transfer issues in multimodal RL for physics reasoning, revealing that models struggle with representation-invariant reasoning and often rely on residual textual cues rather than visual evidence.