SVR-R1: Bootstrapping Multi-modal Reasoning with Self-verification in Reinforcement Learning

Benchmark Model Rank Results
multimodal-reasoning-on-mathvisionSVR-R1 (7B ThinkLite)–Accuracy: 19.1
multimodal-reasoning-on-mathvistaSVR-R1 (7B ThinkLite)–Accuracy: 71.6
vision-language-understanding-on-mmstarSVR-R1 (7B ThinkLite)–Accuracy: 49.3