Publications

2026

1. arXiv

   Point2Part: Unified 3D Partitioning from Point Prompts

   Hao-Tang Tsui, Yu-Rou Tuan, Xiaoxuan Ma, and 3 more authors

   Under review , Sep 2026

   arXiv Bib PDF Website

   @misc{tsui2026point2part,
     author = {Tsui, Hao-Tang and Tuan, Yu-Rou and Ma, Xiaoxuan and Ugrinovic, Nicolas and Shiratori, Takaaki and Kitani, Kris},
     title = {Point2Part: Unified 3D Partitioning from Point Prompts},
     year = {2026},
     month = sep,
     eprint = {2609.38180},
     archiveprefix = {arXiv},
     primaryclass = {cs.CV},
   }

2. arXiv

   SNAP3D: Physically Grounded 3D Parts for Assembly from a Single Image

   Yu-Rou Tuan, Hao-Tang Tsui, Nicolas Ugrinovic, and 2 more authors

   Under review , Sep 2026

   arXiv Bib PDF Website

   @misc{tuan2026snap3d,
     author = {Tuan, Yu-Rou and Tsui, Hao-Tang and Ugrinovic, Nicolas and Kitani, Kris and Ma, Xiaoxuan},
     title = {SNAP3D: Physically Grounded 3D Parts for Assembly from a Single Image},
     year = {2026},
     month = sep,
     eprint = {2609.13146},
     archiveprefix = {arXiv},
     primaryclass = {cs.GR},
   }

3. CVPRw

   

   Σ StaDy4D: Towards Complete 4D Static-Dynamic Reconstruction with SIGMA

   Hao-Tang Tsui, Yu-Rou Tuan, Ethan Lai, and 1 more author

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)Oral, GenRecon3D Workshop , Jun 2026

   Best Paper Bib PDF Website

   Best Paper Award and Oral presentation at the CVPR 2026 Workshop on Generative Models for 3D/4D Reconstruction (GenRecon3D).

   @inproceedings{tsui2026stady4d,
     author = {Tsui, Hao-Tang and Tuan, Yu-Rou and Lai, Ethan and Wang, Chen-Yu},
     title = {{\Sigma} StaDy4D: Towards Complete 4D Static-Dynamic Reconstruction with SIGMA},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
     year = {2026},
     month = jun,
   }

4. CVPRw

   

   Traffic Scene Generation from Natural Language Description for Autonomous Vehicles with Large Language Model

   Bo-Kai Ruan, Hao-Tang Tsui, Yung-Hui Li, and 1 more author

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Jun 2026

   arXiv Bib PDF Video Website

   @inproceedings{ruan2026ttsg,
     author = {Ruan, Bo-Kai and Tsui, Hao-Tang and Li, Yung-Hui and Shuai, Hong-Han},
     title = {Traffic Scene Generation from Natural Language Description for Autonomous Vehicles with Large Language Model},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
     year = {2026},
     month = jun,
     eprint = {2409.09575},
     archiveprefix = {arXiv},
     primaryclass = {cs.RO},
   }

2025

1. ICLR

   

   YOLO-RD: Introducing Relevant and Compact Explicit Knowledge to YOLO by Retriever-Dictionary

   Hao-Tang Tsui, Chien-Yao Wang, and Hong-Yuan Mark Liao

   In Proceedings of the International Conference on Learning Representations (ICLR), Apr 2025

   arXiv Bib PDF Code Website

   @inproceedings{tsui2024yolord,
     author = {Tsui, Hao-Tang and Wang, Chien-Yao and Liao, Hong-Yuan Mark},
     title = {YOLO-RD: Introducing Relevant and Compact Explicit Knowledge to YOLO by Retriever-Dictionary},
     booktitle = {Proceedings of the International Conference on Learning Representations (ICLR)},
     year = {2025},
     month = apr,
     eprint = {2410.15346},
     archiveprefix = {arXiv},
     primaryclass = {cs.CV},
   }

2024

1. ECCV

   

   TrajPrompt: Aligning Color Trajectory with Vision-Language Representations

   Li-Wu Tsao, Hao-Tang Tsui, Yu-Rou Tuan, and 5 more authors

   In Proceedings of the European Conference on Computer Vision (ECCV), Oct 2024

   Bib PDF Website

   @inproceedings{tsao2024trajprompt,
     author = {Tsao, Li-Wu and Tsui, Hao-Tang and Tuan, Yu-Rou and Chen, Pei-Chi and Wang, Kuan-Lin and Wu, Jhih-Ciang and Shuai, Hong-Han and Cheng, Wen-Huang},
     title = {TrajPrompt: Aligning Color Trajectory with Vision-Language Representations},
     booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
     year = {2024},
     month = oct,
   }

2. ECCV

   

   YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

   Chien-Yao Wang, and Hong-Yuan Mark Liao

   In Proceedings of the European Conference on Computer Vision (ECCV), Oct 2024

   arXiv Bib PDF Video Website

   @inproceedings{wang2024yolov9,
     author = {Wang, Chien-Yao and Liao, Hong-Yuan Mark},
     title = {YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information},
     booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
     year = {2024},
     month = oct,
     eprint = {2402.13616},
     archiveprefix = {arXiv},
     primaryclass = {cs.RO},
     publisher = {Vision},
   }

2023

1. 

   POSE: Pose Estimation Of Virtual Sync Exhibit System

   Hao-Tang Tsui, Yu-Rou Tuan, and Jia-You Chen

   Oct 2023

   arXiv Bib

   @misc{tsui2024pose,
     author = {Tsui, Hao-Tang and Tuan, Yu-Rou and Chen, Jia-You},
     title = {POSE: Pose Estimation Of Virtual Sync Exhibit System},
     year = {2023},
     eprint = {2410.15343},
     archiveprefix = {arXiv},
     primaryclass = {cs.AI},
   }

2. 

   IKDP: Inverse Kinematics through Diffusion Process

   Hao-Tang Tsui, Yu-Rou Tuan, and Hong-Han Shuai

   Oct 2023

   arXiv Bib

   @misc{tsui2024ikdp,
     author = {Tsui, Hao-Tang and Tuan, Yu-Rou and Shuai, Hong-Han},
     title = {IKDP: Inverse Kinematics through Diffusion Process},
     year = {2023},
     eprint = {2410.15341},
     archiveprefix = {arXiv},
     primaryclass = {cs.AI},
   }