Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language Models
Yuqi Xiong, Chunyi Peng, Zhipeng Xu +5
Reinforcement learning (RL) can elicit specialized visual capabilities in vision-language models (VLMs), yet jointly optimizing heterogeneous objectives often introduces cross-capa…
cs.CV2026
ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval
Chunyi Peng, Zhipeng Xu, Yukun Yan +9
Visual document retrieval is a critical component of multimodal retrieval-augmented generation, aiming to identify query-relevant pages from document collections where evidence is…