2 papers
cs.AI2025
Causal-LLaVA: Causal Disentanglement for Mitigating Hallucination in Multimodal Large Language Models
Xinmiao Hu, Chun Wang, Ruihe An +4
Multimodal Large Language Models (MLLMs) have demonstrated strong performance in visual understanding tasks, yet they often suffer from object hallucinations--generating descriptio…
cs.CV2025
FocusedAD: Character-centric Movie Audio Description
Xiaojun Ye, Chun Wang, Yiren Song +3
Movie Audio Description (AD) aims to narrate visual content during dialogue-free segments, particularly benefiting blind and visually impaired (BVI) audiences. Compared with genera…