Yunxin Li

LingCloud. Attaching human-like eyes to the large language model. The codes of IEEE TMM paper "LMEye: An Interactive Perception Network for Large Language Model""

Multimodal-Context-Reasoning. A multimodal context reasoning approach that introduce the multi-view semantic alignment information via prefix tuning.

NDCR. A Neural Divide-and-Conquer Reasoning Framework for Multimodal Reasoning on Linguistically Complex Text and Similar Images

Training-LLMs-Towards-Holistic-Learning. Training Language Models From Fragmentation Learning To Holistic Learning