Jaehyeong Jo

Jaehyeong Jo

[Google Scholar] [CV (Curriculum Vitae)]

Contact: harryjo97 [at] kaist.ac.kr

About

I am a postdoctoral researcher at KAIST, working with Prof. Sung Ju Hwang and his research group MLAI lab. I recieved my PhD in Artificial Intelligence at KAIST in 2026, advised by Prof. Sung Ju Hwang. Previously, I was a Research Intern at Meta AI.

My research focuses on generative modeling and representation learning for understanding, predicting, and interacting with the physical world. I am interested in how models can learn the structure and dynamics of their environments to support reasoning, planning, and action. My background includes geometric approaches to diffusion models, with applications to language and scientific discovery.

Publications

Future Representation Distillation for Imagination-free World Action Models

[project page] [paper]
Jaehyeong Jo*, Sangwon Jang*, Sihyun Yu, Seonghyeon Ye, Yekyung Nah, Hojung Jung, Kimin Lee^, Sung Ju Hwang^
Preprint 2026

BlendPO: Controlling Guidance Strength in Reinforcement Learning without Changing Guidance Content

[paper]
Myeongkyun Cho, Hyeonyu Kim, Minki Kang, Jaehyeong Jo, Sung Ju Hwang
Preprint 2026

R-DiT: Recursive Diffusion Transformer

[paper]
Hojung Jung, Youngrok Park, Sihyun Yu, Jaehyeong Jo, Sangwon Jang, Juhyeong Kim, Sangmin Bae, Se-Young Yun
Preprint 2026

Omnilingual SONAR: Cross-Lingual and Cross-Modal Sentence Embeddings Bridging Massively Multilingual Text and Speech

[paper]
Omnilingual SONAR Team, João Maria Janeiro, Pere-Lluís Huguet Cabot, Ioannis Tsiamas, Yen Meng, Vivek Iyer, Guillem Ramírez, Loic Barrault, Belen Alastruey, Yu-An Chung, Marta R. Costa-Jussa, David Dale, Kevin Heffernan, Jaehyeong Jo, Artyom Kozhevnikov, Alexandre Mourachko, Christophe Ropers, Holger Schwenk, Paul-Ambroise Duquenne
Technical report 2026

MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models

[paper]
Hojung Jung, Rodrigo Hormazabal, Jaehyeong Jo, Youngrok Park, Kyunggeun Roh, Se-Young Yun, Sehui Han, Dae-Woong Jeong
NeurIPS 2026

Self-Refining Video Sampling

[project page] [paper] [code]
Sangwon Jang*, Taekyung Ki*, Jaehyeong Jo*, Saining Xie, Jaehong Yoon^, Sung Ju Hwang^
ICML 2026

Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation

[project page] [paper] [code]
Taekyung Ki*, Sangwon Jang*, Jaehyeong Jo, Jaehong Yoon, Sung Ju Hwang
CVPR 2026

Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models

[project page] [paper] [code]
Sangwon Jang*, Taekyung Ki*, Jaehyeong Jo, Jaehong Yoon, Soo Ye Kim, Zhe Lin, Sung Ju Hwang
ICLR 2026

LS-Merge: Merging Language Models in Latent Space

[paper]
Bedionita Soro, Aoxuan Silvia Zhang, Bruno Andreis, Jaehyeong Jo, Song Chong, Sung Ju Hwang
ICLR 2026

Continuous Diffusion Model for Language Modeling

[paper] [code]
Jaehyeong Jo, Sung Ju Hwang
NeurIPS 2025

Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models

[project page] [paper]
Sangwon Jang, June Suk Choi, Jaehyeong Jo, Kimin Lee^, Sung Ju Hwang^
CVPR 2025

Conditional Synthesis of 3D Molecules with Time Correction Sampler

[paper]
Hojung Jung*, Youngrok Park*, Laura Schmid, Jaehyeong Jo, Dongkyu Lee, Bongsang Kim, Se-Young Yun, Jinwoo Shin
NeurIPS 2024

Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models

[project page] [paper] [code]
Sangwon Jang*, Jaehyeong Jo*, Kimin Lee^, Sung Ju Hwang^
NeurIPS 2024

Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes

[paper] [code]
Jaehyeong Jo, Sung Ju Hwang
ICML 2024

Graph Generation with Diffusion Mixture

[paper] [code]
Jaehyeong Jo*, Dongki Kim*, Sung Ju Hwang
ICML 2024

DiffusionNAG: Task-guided Neural Architecture Generation with Diffusion Models

[paper] [code]
Sohyun An*, Hayeon Lee*, Jaehyeong Jo, Seanie Lee, Sung Ju Hwang
ICLR 2024

Text-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models

[project page] [paper]
Jaewoong Lee*, Sangwon Jang*, Jaehyeong Jo, Jaehong Yoon, Yunji Kim, Jin-Hwa Kim, Jung-Woo Ha, Sung Ju Hwang
ICCV 2023

Exploring Chemical Space with Score-based Out-of-distribution Generation

[paper] [code]
Seul Lee, Jaehyeong Jo, Sung Ju Hwang
ICML 2023

Antibody-SGM: Antigen-Specific Joint Design of Antibody Sequence and Structure Using Diffusion Models

[paper]
Xuezhi Xie, Jin Sub Lee, Dongki Kim, Jaehyeong Jo, Jisun Kim, Philip M. Kim
ICML 2023 Workshop on Computational Biology

Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations

[paper] [code] [talk]
Jaehyeong Jo*, Seul Lee*, Sung Ju Hwang
ICML 2022

Edge Representation Learning with Hypergraphs

[paper] [code]
Jaehyeong Jo*, Jinheon Baek*, Seul Lee*, Dongki Kim, Minki Kang, Sung Ju Hwang
NeurIPS 2021

*: Equal contribution, ^: Equal advising

Work Experience

Meta FAIR

Research Intern (Advisor: Loic Barrault)
Jun. 2025 - Sep. 2025, Paris

Meta Reality Labs

Research Intern
May. 2024 - Aug. 2024, Burlingame, CA