2 papers
cs.CV2025
MoCHA: Advanced Vision-Language Reasoning with MoE Connector and Hierarchical Group Attention
Yuqi Pang, Bowen Yang, Yun Cao +3
Vision large language models (VLLMs) are focusing primarily on handling complex and fine-grained visual information by incorporating advanced vision encoders and scaling up visual…
cs.CV2025
Language Models Can See Better: Visual Contrastive Decoding For LLM Multimodal Reasoning
Yuqi Pang, Bowen Yang, Haoqin Tu +2
Although Large Language Models (LLMs) excel in reasoning and generation for language tasks, they are not specifically designed for multimodal challenges. Training Multimodal Large…