Chaehyun Kim

I am an integrated M.S./Ph.D. student of CVLAB at KAIST, advised by Prof. Seungryong Kim and a research intern at Naver Cloud, focusing on the visual components of multi-modal large language models.

My research interests lie at the intersection of computer vision and embodied agents, focusing on developing semantically rich perception and generative models to advance robot perception and world modeling.

If you have any questions or suggestions, please feel free to contact me via email (kchyun@kaist.ac.kr) or LinkedIn!

Publications

teaser Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers

Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers

Chaehyun Kim, Heeseong Shin, Eunbeen Hong, Heeji Yoon, Anurag Arnab, Paul Hongsuck Seo, Sunghwan Hong, Seungryong Kim

In Advances in Neural Information Processing System (NeurIPS), 2025

teaser Visual Representation Alignment for Multimodal Large Language Models

Visual Representation Alignment for Multimodal Large Language Models

Heeji Yoon, Jaewoo Jung, Junwan Kim, Hyungyu Choi, Heeseong Shin, Sangbeom Lim, Honggyu An, Chaehyun Kim, Jisang Han, Donghyun Kim, Chanho Eom, Sunghwan Hong, Seungryong Kim

Arxiv, 2025

teaser D<sup>2</sup>USt3R: Enhancing 3D Reconstruction with 4D Pointmaps for Dynamic Scenes

D²USt3R: Enhancing 3D Reconstruction with 4D Pointmaps for Dynamic Scenes

Jisang Han, Honggyu An, Jaewoo Jung, Takuya Narihira, Junyoung Seo, Kazumi Fukuda, Chaehyun Kim, Sunghwan Hong, Yuki Mitsufuji, and Seungryong Kim.

In Advances in Neural Information Processing Systems (NeurIPS), 2025

teaser Towards open-vocabulary semantic segmentation without semantic labels

Towards open-vocabulary semantic segmentation without semantic labels

Heeseong Shin, Chaehyun Kim, Sunghwan Hong, Seokju Cho, Anurag Arnab, Paul Hongsuck Seo, and Seungryong Kim.

In Advances in Neural Information Processing Systems (NeurIPS), 2024