Edit, Don't Imitate: Minimal-Edit On-Policy Distillation for Multimodal Reasoning
Visual mathematical reasoning can fail before reasoning begins: when a vision-language model (VLM) misreads a diagram, subsequent reasoning proceeds from false premises.
By Wen Ye, Ailin Deng, Zirui Wang, Shixing Yu, Han Zhang, Tian Yun, Nikhil Mehta, Tarun Kalluri, Xuefei Cao, Xuezhe Ma, Hengduo LiarXiv cs.LG
Read the full story
Originally published by arXiv cs.LG on Oct 23, 2026.
Comments
Sign in to join the discussion.