3 papers
cs.CV2026
SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical Reasoning
Xiuwei Chen, Wentao Hu, Hanhui Li +9
Recent advances in multimodal large language models (MLLMs) have shown impressive reasoning capabilities. However, further enhancing existing MLLMs necessitates high-quality vision…
cs.CV2026
Reflect to Inform: Boosting Multimodal Reasoning via Information-Gain-Driven Verification
Shuai Lv, Chang Liu, Feng Tang +5
Multimodal Large Language Models (MLLMs) achieve strong multimodal reasoning performance, yet we identify a recurring failure mode in long-form generation: as outputs grow longer,…
cs.CV2025
PaMi-VDPO: Mitigating Video Hallucinations by Prompt-Aware Multi-Instance Video Preference Learning
Xinpeng Ding, Kui Zhang, Jianhua Han +3
Direct Preference Optimization (DPO) helps reduce hallucinations in Video Multimodal Large Language Models (VLLMs), but its reliance on offline preference data limits adaptability…