Scholar
Daewon Choi
Google Scholar ID: NlcfkbgAAAAJ
KAIST
Citations & Impact
Citations
91
H-index
3
i10-index
1
Publications
7
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- - HAMLET: Switch your Vision-Language-Action Model into a History-Aware Policy, Preprint 2025
- - Think Clearly: Improving Reasoning via Redundant Token Pruning, EMNLP 2025 (Findings), ICML Workshop on Efficient Systems for Foundation Models (ES-FoMo III), 2025
- - Mamba Drafters for Speculative Decoding, EMNLP 2025 (Findings), ICML Workshop on Efficient Systems for Foundation Models (ES-FoMo III), 2025
- - Adversarial Robustification via Text-to-Image Diffusion Models, ECCV 2024, Oral Presentation
- - Modality-agnostic Self-supervised Learning with Meta-Learned Masked Auto-encoder, NeurIPS 2023
- - 3D GAN Inversion with Pose Optimization, WACV 2023
- - AE-NeRF: Auto-Encoding Neural Radiance Fields for 3D-Aware Object Manipulation, Preprint 2022
Research Experience
- - Research Collaboration, Nov. 2022
Education
- - Korea Advanced Institute of Science and Technology (KAIST), M.S & Ph.D. Student in Artificial Intelligence, Feb. 2024 - Present
- - Korea University, B.S. in Industrial Management Engineering and Computer Science, Feb. 2020 - Feb. 2024, GPA: 4.29/4.5 (Great Honors)
Background
- - Research Interests: Practical problems (e.g., efficiency, safety) of multimodal/language foundation models
- - Advisor: Prof. Jinwoo Shin
- - Field: Algorithmic Intelligence Laboratory (ALIN-LAB)
- - About: Ph.D. student at KAIST, received B.S. in Industrial Management Engineering and Computer Science from Korea University
Co-authors