2 papers
cs.CV2025
LISA: A Layer-wise Integration and Suppression Approach for Hallucination Mitigation in Multimodal Large Language Models
Zhihui Guo, Xin Man, Hui Xu +4
Multimodal Large Language Models (MLLMs) excel in vision-language tasks such as image captioning but remain prone to object hallucinations, where they describe objects that do not…
cs.LG2024
Imitation Learning from Suboptimal Demonstrations via Meta-Learning An Action Ranker
Jiangdong Fan, Hongcai He, Paul Weng +2
A major bottleneck in imitation learning is the requirement of a large number of expert demonstrations, which can be expensive or inaccessible. Learning from supplementary demonstr…