Jimin Lee

About

I am a 1st year M.S. & 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 Computer Science & Engineering at Korea University in 2025.

My goal is to build intelligent systems that can perceive, understand, and interact with the world in a human-like manner. To this end, my research focuses on Robotics Foundation Models and Vision-Language-Action (VLA) Models. In particular, I am interested in extending VLA models with additional multimodal inputs that enable better cross-modal alignment and more precise robot control.

Publications

• Selected
• All

Adaptive Temporal Action Quantization for Vision-Language-Action Models

Hojin Jeon^*, Jimin Lee^*, Myungkyu Koo, Jinwoo Shin

Preprint

RLDX-1 Technical Report

Dongyoung Kim^*§, Huiwon Jang^*§, Myungkyu Koo^*, Suhyeok Jang^*, Taeyoung Kim^*, …, Jimin Lee, and 61 more authors, Jinwoo Shin^§ Jimin Lee is a core contributor to this project.

RLWRLD Technical Report, 2026

Paper Website Code

Modular Sensory Stream for Integrating Physical Feedback in Vision-Language-Action Models

Jimin Lee, Huiwon Jang, Myungkyu Koo, Jungwoo Park, Jinwoo Shin

Preprint

Paper Website

Contrastive Representation Regularization for Vision-Language-Action Models

Taeyoung Kim, Jimin Lee, Myungkyu Koo, Dongyoung Kim, Kyungmin Lee, Changyeon Kim, Younggyo Seo, Jinwoo Shin

International Conference on Machine Learning (ICML), 2026

Paper

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

Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025 (Findings)
ICML Workshop on Efficient Systems for Foundation Models (ES-FoMo III), 2025

Paper Poster

SoccerNet 2024 Challenges Results

SoccerNet Challenge Participants

CVPR Workshop on SoccerNet Challenge, 2024

Paper

Adaptive Temporal Action Quantization for Vision-Language-Action Models

Hojin Jeon^*, Jimin Lee^*, Myungkyu Koo, Jinwoo Shin

Preprint

RLDX-1 Technical Report

Dongyoung Kim^*§, Huiwon Jang^*§, Myungkyu Koo^*, Suhyeok Jang^*, Taeyoung Kim^*, …, Jimin Lee, and 61 more authors, Jinwoo Shin^§ Jimin Lee is a core contributor to this project.

RLWRLD Technical Report, 2026

Paper Website Code

Modular Sensory Stream for Integrating Physical Feedback in Vision-Language-Action Models

Jimin Lee, Huiwon Jang, Myungkyu Koo, Jungwoo Park, Jinwoo Shin

Preprint

Paper Website

Contrastive Representation Regularization for Vision-Language-Action Models

Taeyoung Kim, Jimin Lee, Myungkyu Koo, Dongyoung Kim, Kyungmin Lee, Changyeon Kim, Younggyo Seo, Jinwoo Shin

International Conference on Machine Learning (ICML), 2026

Paper

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

Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025 (Findings)
ICML Workshop on Efficient Systems for Foundation Models (ES-FoMo III), 2025

Paper Poster

SoccerNet 2024 Challenges Results

SoccerNet Challenge Participants

CVPR Workshop on SoccerNet Challenge, 2024

Paper

Education

Experience

Honors and Awards

Academic Services

• Workshop Reviewer: ES-FoMo III @ ICML 2025