Publications

2026

  1. soon.png
    Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning
    Jisoo Kim,  Sangwon Baik, Taeksoo Kim, Sungjoo Kim, Junyoung Lee, Mingi Choi, Hanbyul Joo
    arXiv 2026
    Paper Project Page
  2. simuscene.gif
    SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image
    Inhee Lee*,  Sangwon Baik*, Sungjoo Kim, Hyeonwoo Kim, Hyunsoo Cha, Hanbyul Joo
    arXiv 2026
    Paper Code Project Page
  3. vlmpose.webp
    Text-Guided 6D Object Pose Rearrangement via Closed-Loop VLM Agents
    Sangwon Baik, Gunhee Kim, Mingi Choi, Hanbyul Joo
    ECCV 2026
    Paper Code Project Page

2025

  1. hhoi.webp
    Learning to Generate Human-Human-Object Interactions from Textual Descriptions
    Jeonghyeon Na*,  Sangwon Baik*, Inhee Lee, Junyoung Lee, Hanbyul Joo
    NeurIPS 2025
    Paper Code Project Page
  2. oor.gif
    Learning 3D Object Spatial Relationships from Pre-trained 2D Diffusion Models
    Sangwon Baik, Hyeonwoo Kim, Hanbyul Joo
    ICCV 2025
    Paper Code Project Page
  3. david.gif
    DAViD: Modeling Dynamic Affordance of 3D Objects using Pre-trained Video Diffusion Models
    Hyeonwoo Kim,  Sangwon Baik, Hanbyul Joo
    ICCV 2025
    Paper Code Project Page

2022

  1. anna.png
    ANNA: Specialized Architecture for Approximate Nearest Neighbor Search
    Yejin Lee, Hyunji Choi, Sunhong Min, Hyunseung Lee,  Sangwon Baik, Dawoon Jeong, Jae W. Lee, TaeJun Ham
    HPCA 2022
    Paper