works on
inference-time refinement 1multimodal reasoning 1reinforcement learning 1self-verification 1vision-language models 1

From the 1 of 2 linked papers with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

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

Mingyuan Wu, Jingcheng Yang, Shengyi Qian +11

The paper introduces SVR-R1, a reinforcement learning framework that lets a multimodal model generate an answer and then self‑verify it with a binary verdict, allowing a second‑cha…