Joon Son Chung

Associate Professor, KAIST

3 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

1 paper

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision

#3611 · Chenshuang Zhang, Kang Zhang, Joon Son Chung, In So Kweon, Junmo Kim, Chengzhi Mao

Poster Session 2

1 paper

Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation

#4605 · Kang Zhang, Trung X. Pham, Suyeon Lee, Axi Niu, Arda Senocak, Joon Son Chung

We introduce MGAudio, a flow-based framework for video-to-audio generation that leverages model-guided dual-role alignment to achieve state-of-the-art performance.

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.