Causal Decoding for Hallucination-Resistant Multimodal Large Language Models

This research introduces a causal decoding framework that mitigates object hallucination in multimodal large language models through targeted token-level int...

Level: advanced

By Shiwei Tan, Hengyi Wang, Weiyi Qin, Qi Xu, Zhigang Hua, Hao Wang

Category: research