Hello, I'm Jiwon Kang

I am an Integrated M.S./Ph.D. student at KAIST AI (Kim Jaechul Graduate School of AI), advised by Seungryong Kim (CVLAB). Having started my research career in 3D vision, I expanded my focus during my Master's to Generative AI, including its practical applications, and Unified Multimodal Models (UMMs). Recently, I have become interested in the challenge of world modeling by combining 3D vision capabilities with generative knowledge, which can be extended to real-world robotics and immersive gaming environments.

CV Scholar Github Linkedin

News

Experience

Kakao, Seoul
Research Intern
  • Worked on Text-to-Speech research, repurposing Whisper as a continuous tokenizer for autoregressive diffusion-based TTS model
Mar – May 2026

Publications

* denotes equal contribution.  ·  † denotes corresponding author.

2026

Transferability Between Understanding and Generation in Unified Multimodal Models

Transferability Between Understanding and Generation in Unified Multimodal Models

Jiwon Kang*, Heeji Yoon*, Jaewoo Jung, Jaewon Min, Minkyeong Jeon, Biyeon Hwang, Sangwon Jung, Seungryong Kim†
ECCV
  • Investigated how understanding and generation capabilities (e.g., counting) transfer to one another within unified multimodal models.
  • Showed that transferability depends on the model architecture, and proposed a practical post-training strategy for unified multimodal models that leverages transferability.
Project Page PDF arXiv Code
APPLE: Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping

APPLE: Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping

Jiwon Kang*, Yeji Choi*, JoungBin Lee, Wooseok Jang, Jinhyeok Choi, Taekeun Kang, Yongjae Park, Myungin Kim, Seungryong Kim†
CVPR
  • Prior diffusion-based face swapping methods focused on changing facial identity, failing to preserve facial attributes.
  • Proposed a novel pseudo-labeling framework that preserves facial attributes while swapping identities, achieving Pareto-optimal results.
Project Page PDF arXiv Code
A Noise is Worth Diffusion Guidance

A Noise is Worth Diffusion Guidance

Donghoon Ahn*, Jiwon Kang*, Sanghyun Lee, Jaewon Min, Wooseok Jang, Minjae Kim, Hyungwon Cho, Sayak Paul, SeonHwa Kim, Eunju Cha†, Kyong Hwan Jin†, Seungryong Kim†
ICLR
  • Showed that classifier-free guidance can be replaced by refining the initial noise.
  • Enabled high-quality generation without a guidance pass, highlighting the importance of the initial noise in diffusion models.
Project Page PDF arXiv Code

2025

Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models

Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models

Donghoon Ahn*, Jiwon Kang*, Sanghyun Lee, Minjae Kim, Wooseok Jang, Jaewon Min, Sangwu Lee, Sayak Paul, Seungryong Kim†
NeurIPS
  • Systematically studied perturbation guidance in diffusion and flow models.
  • Showed that perturbing different layers/heads in a diffusion model exhibits different effects on the generated samples, which can be systematically combined to improve user-specified attributes via the proposed framework.
Project Page PDF arXiv Code
Self-Evolving Neural Radiance Fields

Self-Evolving Neural Radiance Fields

Jaewoo Jung*, Jisang Han*, Jiwon Kang*, Seongchan Kim, Min-Seop Kwak, Seungryong Kim†
ICCVW
  • Proposed a self-training framework that lets a NeRF improve itself from few input views via pseudo-label distillation.
Project Page PDF arXiv Code

Preprints & Under Review

RAIN-GS: Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting

RAIN-GS: Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting

Jaewoo Jung*, Jisang Han*, Honggyu An*, Jiwon Kang*, Seonghoon Park*, Seungryong Kim†
arXiv 350+ Stars
  • Relaxed the accurate point-cloud initialization requirement of 3D Gaussian Splatting, enabling training from sparse or random initialization.
Project Page PDF arXiv Code