Chaeyoung Jung

PhD student, KAIST, Korea Advanced Institute of Science & Technology

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

1 paper

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding

#1907 · Chaeyoung Jung, Youngjoon Jang, Joon Son Chung

We introduce Audio-Visual Contrastive Decoding (AVCD), a training-free framework for mitigating hallucinations in AV-LLMs by reformulating the existing contrastive decoding framework to support trimodal interactions.