2026

Toward Structural Multimodal Representations: Specialization, Selection, and Sparsification via Mixture-of-Experts
Toward Structural Multimodal Representations: Specialization, Selection, and Sparsification via Mixture-of-Experts

Hahyeon Choi, Nojun Kwak

International Conference on Machine Learning (ICML) 2026

[Paper] [Summary]

Toward Structural Multimodal Representations: Specialization, Selection, and Sparsification via Mixture-of-Experts

Hahyeon Choi, Nojun Kwak

International Conference on Machine Learning (ICML) 2026

[Paper] [Summary]

2025

What's Making That Sound Right Now? Video-centric Audio-Visual Localization
What's Making That Sound Right Now? Video-centric Audio-Visual Localization

Hahyeon Choi, Junhoo Lee, Nojun Kwak

International Conference on Computer Vision (ICCV) 2025

[Paper] [Data] [Project]

What's Making That Sound Right Now? Video-centric Audio-Visual Localization

Hahyeon Choi, Junhoo Lee, Nojun Kwak

International Conference on Computer Vision (ICCV) 2025

[Paper] [Data] [Project]

2024

GrowOVER: How Can LLMs Adapt to Growing Real-World Knowledge?
GrowOVER: How Can LLMs Adapt to Growing Real-World Knowledge?

Dayoon Ko, Jinyoung Kim, Hahyeon Choi, Gunhee Kim

Annual Meeting of the Association for Computational Linguistics (ACL) 2024

[Paper] [Code]

GrowOVER: How Can LLMs Adapt to Growing Real-World Knowledge?

Dayoon Ko, Jinyoung Kim, Hahyeon Choi, Gunhee Kim

Annual Meeting of the Association for Computational Linguistics (ACL) 2024

[Paper] [Code]

VLAAD: Vision and Language Assistant for Autonomous Driving
VLAAD: Vision and Language Assistant for Autonomous Driving

SungYeon Park, MinJae Lee, JiHyuk Kang, Hahyeon Choi, Yoonah Park, Juhwan Cho, Adam Lee, DongKyu Kim

WACV 2024 Workshops on Large Language and Vision Models for Autonomous Driving (LLVM-AD) 2024

[Paper] [Code]

VLAAD: Vision and Language Assistant for Autonomous Driving

SungYeon Park, MinJae Lee, JiHyuk Kang, Hahyeon Choi, Yoonah Park, Juhwan Cho, Adam Lee, DongKyu Kim

WACV 2024 Workshops on Large Language and Vision Models for Autonomous Driving (LLVM-AD) 2024

[Paper] [Code]