Weipeng Chen

6

Papers

76

Total Citations

Papers (6)

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning

Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs

KV Shifting Attention Enhances Language Modeling

Beyond Sight: Towards Cognitive Alignment in LVLM via Enriched Visual Knowledge

Efficient Motion-Aware Video MLLM

Improving Accuracy and Calibration via Differentiated Deep Mutual Learning