Daewon Choi
Graduate student at KAIST
KAIST AI
daeone0920 [AT] kaist.ac.kr
About
I am a Ph.D. student at Algorithmic Intelligence Laboratory (ALIN-LAB), advised by Prof. Jinwoo Shin at Korea Advanced Institute of Science and Technology (KAIST). I received my B.S. in Industrial Management Engineering and Computer Science at Korea University in 2024. My recent research interests focus on practical problems (e.g., efficiency, safety) of multimodal/language foundation models.
Publications
Think Clearly: Improving Reasoning via Redundant Token Pruning
Daewon Choi, Jimin Lee, Jihoon Tack, Woomin Song, Saket Dingliwal, Sai Muralidhar Jayanthi, Bhavana Ganesh, Jinwoo Shin, Aram Galstyan, Sravan Babu Bodapati
Preprint, 2025
Mamba Drafters for Speculative Decoding
Daewon Choi, Seunghyuk Oh, Saket Dingliwal, Jihoon Tack, Woomin Song, Seojin Kim, Insu Han, Jinwoo Shin, Aram Galstyan, Shubham Katiyar, Sravan Babu Bodapati
Arxiv preprint, 2025
Adversarial Robustification via Text-to-Image Diffusion Models
Daewon Choi*, Jongheon Jeong*, Huiwon Jang, Jinwoo Shin
European Conference on Computer Vision (ECCV), 2024, Oral Presentation (200/8585=2.3%)
Modality-agnostic Self-supervised Learning with Meta-Learned Masked Auto-encoder
Huiwon Jang*, Jihoon Tack*, Daewon Choi, Jongheon Jeong, Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2023
3D GAN Inversion with Pose Optimization
Jaehoon Ko*, Kyusun Cho*, Daewon Choi, Kwangrok Ryoo, Seungryong Kim
Winter Conference on Applications of Computer Vision (WACV), 2023
AE-NeRF: Auto-Encoding Neural Radiance Fields for 3D-Aware Object Manipulation
Mira Kim*, Jaehoon Ko*, Kyusun Cho, Junmyeong Choi, Daewon Choi, Seungryong Kim
Arxiv preprint, 2022
Think Clearly: Improving Reasoning via Redundant Token Pruning
Daewon Choi, Jimin Lee, Jihoon Tack, Woomin Song, Saket Dingliwal, Sai Muralidhar Jayanthi, Bhavana Ganesh, Jinwoo Shin, Aram Galstyan, Sravan Babu Bodapati
Preprint, 2025
Mamba Drafters for Speculative Decoding
Daewon Choi, Seunghyuk Oh, Saket Dingliwal, Jihoon Tack, Woomin Song, Seojin Kim, Insu Han, Jinwoo Shin, Aram Galstyan, Shubham Katiyar, Sravan Babu Bodapati
Arxiv preprint, 2025
Adversarial Robustification via Text-to-Image Diffusion Models
Daewon Choi*, Jongheon Jeong*, Huiwon Jang, Jinwoo Shin
European Conference on Computer Vision (ECCV), 2024, Oral Presentation (200/8585=2.3%)
Modality-agnostic Self-supervised Learning with Meta-Learned Masked Auto-encoder
Huiwon Jang*, Jihoon Tack*, Daewon Choi, Jongheon Jeong, Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2023
3D GAN Inversion with Pose Optimization
Jaehoon Ko*, Kyusun Cho*, Daewon Choi, Kwangrok Ryoo, Seungryong Kim
Winter Conference on Applications of Computer Vision (WACV), 2023
AE-NeRF: Auto-Encoding Neural Radiance Fields for 3D-Aware Object Manipulation
Mira Kim*, Jaehoon Ko*, Kyusun Cho, Junmyeong Choi, Daewon Choi, Seungryong Kim
Arxiv preprint, 2022
Education
Korea Advanced Institute of Science and Technology (KAIST)Feb. 2024 - Present
M.S & Ph.D. Student in Artificial Intelligence
Korea UniversityFeb. 2020 - Feb. 2024
B.S. in Industrial Management Engineering and Computer Science
Experience
Research CollaborationNov. 2024 - Current
Undergraduate Research InternFeb. 2023 - Feb. 2024
Meta-Learning Team in ALIN-LAB
Undergraduate Research InternJan. 2022 - Dec. 2022
3D Vision Team in CVLAB
Honors & Awards
National Science & Technology ScholarshipFeb. 2022 - Feb. 2024
Academic Excellence Award (Dean's List)Jun. 2021