On Asymmetric Optimization of Reasoning and Perception in Vision-Language Model Post-Training 文章

ArXiv CS.CV2026-05-29NEWSen作者: Xueqing Wu, Yu-Chi Lin, Kai-Wei Chang, Nanyun Peng

查看原文 →

On Asymmetric Optimization of Reasoning and Perception in Vision-Language Model Post-Training · 相关技术

相关技术

chain-of-thought chain-of-thought supervision Supervised Fine-Tuning Vision-Language Models post-training