Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Beyond Next-Token Alignment: Distilling Multimodal Large Language Models via Token Interactions
Lin Chen, Xiaoke Zhao, Kun Ding +9
Multimodal Large Language Models (MLLMs) demonstrate impressive cross-modal capabilities, yet their substantial size poses significant deployment challenges. Knowledge distillation…
cs.CV2025
ViRC: Enhancing Visual Interleaved Mathematical CoT with Reason Chunking
Lihong Wang, Liangqi Li, Weiwei Feng +6
CoT has significantly enhanced the reasoning ability of LLMs while it faces challenges when extended to multimodal domains, particularly in mathematical tasks. Existing MLLMs typic…