讲者及论文工作介绍:
周冠宇,香港科技大学 (广州) 访问学生,Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality
代彦琪,中国人民大学博士生,MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents
叶加博,阿里巴巴通义实验室 高级算法工程师,mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models
黄明鑫,华南理工大学博士生,Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramid
王晨曦,浙江大学硕士生,MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation