Causal Decoding for Hallucination-Resistant Multimodal Large Language Models
arXiv:2602.21441v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) deliver detailed responses on vision-language tasks, yet remain susceptible to object hallucination (introducing objects not …
Shiwei Tan, Hengyi Wang, Weiyi Qin, Qi Xu, Zhigang Hua, Hao Wang
4 views