Publications

2026

  1. tbd.png
    ACID: Action Consistency via Inverse Dynamics for Planning with World Models
    Gawon Seo, Dongwon Kim, and Suha Kwak
    In arXiv preprint, Jul 2026
    arXiv
  2. 8world.png
    Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model
    Dongwon Kim, Gawon Seo, Jinsung Lee, Minsu Cho, and Suha Kwak
    In CVPR, Jun 2026
    (An early version appeared in LSRW workshop in CoRL 2025)
    arXiv Code Website
  3. tbd.png
    Structured State-Space Regularization for Generation-Friendly Image Tokenization
    Jinsung Lee, Jaemin Oh, Namhun Kim, Dongwon Kim, Byung-Jun Yoon, and Suha Kwak
    In arXiv preprint, Apr 2026
    arXiv

2025

  1. maskgen.png
    Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens
    Dongwon Kim*, Ju He*, Qihang Yu*, Chenglin Yang, Xiaohui Shen, Suha Kwak, and Liang-Chieh Chen
    In ICCV, Jan 2025
    arXiv PDF Code

2024

  1. 158flux.png
    1.58-bit FLUX
    Chenglin Yang, Celong Liu, Xueqing Deng, Dongwon Kim, Xing Mei, Xiaohui Shen, and Liang-Chieh Chen
    In arXiv preprint, Dec 2024
    arXiv
  2. selfmod.png
    Bootstrapping Top-down Information for Self-modulating Slot Attention
    Dongwon Kim, Seoyeon Kim, and Suha Kwak
    In NeurIPS, Dec 2024
    arXiv Code
  3. plot.png
    PLOT: Text-based Person Search with Part Slot Attention for Corresponding Part Discovery
    Jicheol Park, Dongwon Kim, Boseung Jeong, and Suha Kwak
    In ECCV, Oct 2024
  4. risclip.jpg
    Extending CLIP’s Image-Text Alignment to Referring Image Segmentation
    Seoyeon Kim, Minguk Kang, Dongwon Kim, Jaesik Park, and Suha Kwak
    In NAACL, Jun 2024
    Code

2023

  1. sag.png
    Shatter and Gather: Learning Referring Image Segmentation with Text Supervision
    Dongwon Kim*, Namyup Kim*, Cuiling Lan, and Suha Kwak
    In ICCV, Oct 2023
    arXiv Code Website
  2. dive.png
    Improving Cross-Modal Retrieval With Set of Diverse Embeddings
    Dongwon Kim, Namyup Kim, and Suha Kwak
    In CVPR, Jun 2023
    (Highlight, 235/9155 = 2.5%)
    arXiv Code Website

2022

  1. restr.png
    ReSTR: Convolution-Free Referring Image Segmentation Using Transformers
    Namyup Kim, Dongwon Kim, Cuiling Lan, Wenjun Zeng, and Suha Kwak
    In CVPR, Jun 2022
    arXiv Website
  2. stml.png
    Self-Taught Metric Learning Without Labels
    Sungyeon Kim, Dongwon Kim, Minsu Cho, and Suha Kwak
    In CVPR, Jun 2022
    arXiv Code Website

2021

  1. et.png
    Embedding Transfer With Label Relaxation for Improved Metric Learning
    Sungyeon Kim, Dongwon Kim, Minsu Cho, and Suha Kwak
    In CVPR, Jun 2021
    arXiv Website

2020

  1. pa.gif
    Proxy Anchor Loss for Deep Metric Learning
    Sungyeon Kim, Dongwon Kim, Minsu Cho, and Suha Kwak
    In CVPR, Jun 2020
    arXiv Code Website