Preprint
Nov 2026
DreamRealm: Exploring and Materializing Hallucination Worlds for Trustworthy Vision-Language Models
Multimodal large language models (MLLMs) remain prone to visual hallucinations when correct responses depend on subtle visual details. One line of post-training methods constructs visual contrasts through image retrieval, generation, or editing to improve fine-grained perception. However, these contrasts are not built...
Ben-Lei Cui, Chun-Yang Chai, Yi-Liang Zhang et al.
· 0 citations