Huiwon Jang

About

I am a PhD student at Korea Advanced Institute of Science and Technology (KAIST), advised by Prof. Jinwoo Shin. Prior to this, I received B.S. in Mathematical Science and Computer Science at KAIST in 2023. My research interests lie in representation learning and robotic foundation models, along with their applications. Recently, I have been particularly focused on developing vision-language-action models (VLAs) that better perceive visual content and understand the physical world.

Publications

Selected
All

RLDX-1 Technical Report

Huiwon Jang^*§, Dongyoung Kim^*§, Myungkyu Koo^*, Suhyeok Jang^*, Taeyoung Kim^*, Beomjun Kim, Byungjun Yoon, Changsung Jang, Daewon Choi, Dongsu Han, Donguk Lee, Heeseung Kwon, Hojin Jeon, Jaehyun Kang, Jaekyoung Bae, Jihyuk Lee, Jimin Lee, John Won, Joonwoo Ahn, Junhyeong Park, Junyoung Sung, Kyungmin Lee, Minseong Han, Minsung Yoon, Sejune Joo, Seonil Son, Seungcheol Park, Seunggeun Cho, Seungjun Moon, Seungku Kim, Yonghoon Dong, Yongjin Cho, Youngchan Kim, Chang Hwan Kim, Dohyeon Kim, Heecheol Kim, Heewon Lee, Hensen Ahn, Hyungkyu Ryu, Hyunsoo Choi, Hyunsoo Shin, Jaeheon Jung, Jaewoo Kim, Jinwook Kim, Joochul Chang, Joonsoo Kim, Junghun Park, Jungwoo Park, Junho Cho, Junhyeok Park, Junwon Lee, Kangwook Lee, Kwanghoon Kim, Kyoungwhan Choe, Manoj Bhadu, Nayoung Oh, Sangjun Kim, Sangwoo Kim, Seunghoon Shim, Seunghyun Kim, Seungjun Lee, Seungyup Ka, Sungryol Yang, Wook Jung, Yashu Shukla, Yeonjae Lee, Yeonwoo Bae, Jinwoo Shin^§

Technical Report, 2026

Arxiv Website Code

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

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

Arxiv preprint, 2026

Arxiv Website

Dual-stream diffusion for world-model augmented vision-language-action model

John Won, Kyungmin Lee, Huiwon Jang, Dongyoung Kim, Jinwoo Shin

ICML 2026

Arxiv

ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context

Huiwon Jang, Sihyun Yu, Heeseung Kwon, Hojin Jeon, Younggyo Seo^*, Jinwoo Shin^*

Arxiv preprint, 2025

Arxiv Website Code

Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics

Dongyoung Kim, Sumin Park, Huiwon Jang, Jinwoo Shin, Jaehyung Kim^*, Younggyo Seo^*

NeurIPS 2025

Arxiv

SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning

Byungwoo Jeon^*, Dongyoung Kim^*, Huiwon Jang, Insoo Kim, Jinwoo Shin

NeurIPS 2025 Workshop on Space in Vision, Language, and Embodied AI

Arxiv

Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction

Huiwon Jang, Sihyun Yu, Jinwoo Shin, Pieter Abbeel, Younggyo Seo

CVPR 2025

Arxiv Website Code

Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

Sihyun Yu, Sangkyung Kwak, Huiwon Jang, Jongheon Jeong, Jonathan Huang, Jinwoo Shin, Saining Xie

ICLR 2025, Oral Presentation (207/11672=1.77%)

Arxiv Website Code

Visual Representation Learning with Stochastic Frame Prediction

Huiwon Jang, Dongyoung Kim, Junsu Kim, Jinwoo Shin, Pieter Abbeel, Younggyo Seo

ICML 2024

Paper Arxiv Website Poster Code

Modality-agnostic Self-supervised Learning with Meta-learned Masked Auto-encoder

Huiwon Jang^*, Jihoon Tack^*, Daewon Choi, Jongheon Jeong, Jinwoo Shin

NeurIPS 2023

Paper Arxiv Slides Poster Code

Unsupervised Meta-learning via Few-shot Pseudo-supervised Contrastive Learning

Huiwon Jang^*, Hankook Lee^*, Jinwoo Shin

ICLR 2023, Spotlight Presentation (280/4956=5.6%)

NeurIPSW-MetaLearn 2022

Paper Arxiv Slides Poster Code

RLDX-1 Technical Report

Technical Report, 2026

Arxiv Website Code

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

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

Arxiv preprint, 2026

Arxiv Website

RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models

Dongyoung Kim, Sumin Park, Woomin Song, Seungku Kim, Taeyoung Kim, Huiwon Jang, Jinwoo Shin, Jaehyung Kim^*, Younggyo Seo^*

Arxiv preprint, 2026

Arxiv

Dual-stream diffusion for world-model augmented vision-language-action model

John Won, Kyungmin Lee, Huiwon Jang, Dongyoung Kim, Jinwoo Shin

ICML 2026

Arxiv

ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context

Huiwon Jang, Sihyun Yu, Heeseung Kwon, Hojin Jeon, Younggyo Seo^*, Jinwoo Shin^*

Arxiv preprint, 2025

Arxiv Website Code

Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics

Dongyoung Kim, Sumin Park, Huiwon Jang, Jinwoo Shin, Jaehyung Kim^*, Younggyo Seo^*

NeurIPS 2025

Arxiv

SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning

Byungwoo Jeon^*, Dongyoung Kim^*, Huiwon Jang, Insoo Kim, Jinwoo Shin

NeurIPS 2025 Workshop on Space in Vision, Language, and Embodied AI

Arxiv

Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction

Huiwon Jang, Sihyun Yu, Jinwoo Shin, Pieter Abbeel, Younggyo Seo

CVPR 2025

Arxiv Website Code

Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

Sihyun Yu, Sangkyung Kwak, Huiwon Jang, Jongheon Jeong, Jonathan Huang, Jinwoo Shin, Saining Xie

ICLR 2025, Oral Presentation (207/11672=1.77%)

Arxiv Website Code

TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation

Seong Hyeon Park, Huiwon Jang, Byungwoo Jeon, Sukmin Yun, Paul Hongsuck Seo, Jinwoo Shin

NeurIPS 2024, Spotlight Presentation (326/15671=2%)

Paper

Adversarial Robustification via Text-to-Image Diffusion Models

Daewon Choi^*, Jongheon Jeong^*, Huiwon Jang, Jinwoo Shin

ECCV 2024, Oral Presentation (200/8585=2.3%)

Arxiv Code

Visual Representation Learning with Stochastic Frame Prediction

Huiwon Jang, Dongyoung Kim, Junsu Kim, Jinwoo Shin, Pieter Abbeel, Younggyo Seo

ICML 2024

Paper Arxiv Website Poster Code

Modality-agnostic Self-supervised Learning with Meta-learned Masked Auto-encoder

Huiwon Jang^*, Jihoon Tack^*, Daewon Choi, Jongheon Jeong, Jinwoo Shin

NeurIPS 2023

Paper Arxiv Slides Poster Code

Unsupervised Meta-learning via Few-shot Pseudo-supervised Contrastive Learning

Huiwon Jang^*, Hankook Lee^*, Jinwoo Shin

ICLR 2023, Spotlight Presentation (280/4956=5.6%)

NeurIPSW-MetaLearn 2022

Paper Arxiv Slides Poster Code

AltUB: Alternating Training Method to Update Base Distribution of Normalizing Flow for Anomaly Detection

Yeongmin Kim^*, Huiwon Jang^*, Dongkeon Lee, Hojin Choi

Arxiv preprint, 2022

Arxiv

Education

Korea Advanced Institute of Science and Technology (KAIST)Mar. 2023 - Present

PhD. Student in Artificial Intelligence

Korea Advanced Institute of Science and Technology (KAIST)Mar. 2019 - Feb. 2023

B.S. in Mathematical Science and Computer Science

Experience

Visiting Research FellowJun. 2025 -

RLWRLD

Co-leading research on RLDX-1

AI Research InternOct. 2022 - Oct. 2023

i-SENS

Academic Services

Conference Reviewer, IJCAI'23; NeurIPS'24-26; ICLR'25-26; ICML'25-26; CVPR'25-26; ICCV'25; ECCV'26; AISTATS'25

Journal Reviewer, IJCV

Honors & Awards

Travel Award, International Conference on Machine Learning (ICML) 2024Jul. 2024

Travel Award, Conference on Neural Information Processing Systems (NeurIPS) 2023 Dec. 2023

Travel Award, International Conference on Learning Representations (ICLR) 2023 May. 2023

Recipient, Google Conference Scholarships (APAC)May. 2023

Invited Talks

Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder

Samsung Electronics Device Solution (DS)Oct. 2024

Samsung AI Forum (SAIF) 2023Nov. 2023

Samsung Advanced Institue of Technology (SAIT)Jun. 2023

Unsupervised Meta-learning via Few-shot Pseudo-supervised Contrastive Learning

International Conference on Learning Representations (ICLR)May. 2023