2 papers
cs.CV2026
NAS-PO: Native Attention-Strategy Policy Optimization for Vision-Language Models
Ke An, Shizhe Xiang, Yue Liu +5
Reinforcement learning with verifiable rewards (RLVR) has become an effective post-training paradigm for vision-language models (VLMs). Standard RLVR, however, assigns identical ou…
cs.AI2026
Teaching the Way, Not the Answer: Privileged Tutoring Distillation for Multimodal Policy Optimization
Shizhe Xiang, Ke An, Wenlong Yu +5
Recent post-training methods, particularly Reinforcement Learning with Verifiable Rewards (RLVR), have significantly enhanced the reasoning ability of Large Vision-Language Models…