Sibei Yang

ShanghaiTech University. SIST. 1C403.D.

prof.jpeg

Sibei Yang is an Assistant Professor in SIST, ShanghaiTech University, since Fall 2021. Before that, She is a Research Assistant Professor in Computing at The Hong Kong Polytechnic University. She received her Ph.D. degree from the University of Hong Kong in 2020, advised by Prof. Yizhou Yu. Her Ph.D. study is supported by Hong Kong PhD Fellowship. She obtained her B.S. degree in computer science from Chu Kochen Honors College at Zhejiang University in 2016.

Her general research interests span computer vision, natural language processing, and the intersection of them.

Research Lab

░██████╗░█████╗░░█████╗░██╗░░░░░░█████╗░██████╗░
██╔════╝██╔══██╗██╔══██╗██║░░░░░██╔══██╗██╔══██╗
╚█████╗░██║░░██║██║░░██║██║░░░░░███████║██████╦╝
░╚═══██╗██║░░██║██║░░██║██║░░░░░██╔══██║██╔══██╗         
██████╔╝╚█████╔╝╚█████╔╝███████╗██║░░██║██████╦╝       # Welcome to SIST.1C313.
╚═════╝░░╚════╝░░╚════╝░╚══════╝╚═╝░░╚═╝╚═════╝░       # Have Fun!

Our current research interests primarily focus on 1) Open-world Visual Understanding, 2) Neural Generation and Editing, 3) Vision-Language Joint Understanding, 4) Large Language and Vision Models, and 5) Embodied AI. Our mission is to facilitate the learning of unified and universal perception, understanding, reasoning, and generation within the realm of an open world. We believe that learning from multimodal information (especially vision and language) in a general and unified manner, holds the key to a deeper understanding of our world.

We are always looking for undergraduate and graduate students!


News

Jul 5, 2024 Three papers are accepted by ECCV 2024 🎉🎉🎉
Feb 27, 2024 Two papers are accepted by CVPR 2024 🎊🎊🎊
Jan 15, 2024 One paper is accepted by ICLR 2024 🐲🐲🐲
Dec 30, 2023 Congratulations to Cheng Shi for receiving the National Scholarship, and to Jiajin Tang for achieving the Outstanding Student Award.👏👏👏
Sep 23, 2023 2 papers Free-Bloom (Zero-Shot Text-to-Video Generation) and DDCoT (CoT Prompting for Multimodal Reasoning in LMs) are accepted by NeurIPS 2023 🎉🎉🎉

Recent Publication

* equal contribution; † corresponding author.

2024

  1. Part2Object.png
    Part2Object: Hierarchical Unsupervised 3D Instance Segmentation
    Accepted by ECCV, 2024
  2. Plain-D.png
    Plain-DNet: A Plain Multi-Dataset Object Detector
    Accepted by ECCV, 2024
  3. wildrefer.png
    WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural Language
    Zhenxiang Lin, Xidong Peng, Peishan Cong, Ge Zheng, Yujing Sun, Yuenan Hou, Xinge Zhu, Sibei Yang, Yuexin Ma
    Accepted by ECCV, 2024
  4. CVPR2024
    Curriculum Point Prompting for Weakly-Supervised Referring Image Segmentation
    Accepted by CVPR, 2024
  5. devil.png
    The Devil is in the Object Boundary: Towards Annotation-free Instance Segmentation Using Foundation Models
    Accepted by ICLR, 2024
  6. omg.png
    OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers
    Han Liang, Jiacheng Bao, Ruichi Zhang, Sihan Ren, Yuecheng Xu, Sibei Yang, Xin Chen, Jingyi Yu, Lan Xu
    Accepted by CVPR, 2024
  7. RealDex.png
    RealDex: Towards Human-like Grasping for Robotic Dexterous Hand
    Yumeng Liu*, Yaxun Yang*, Youzhuo Wang*, Xiaofei Wu, Jiamin Wang, Yichen Yao, Sören Schwertfeger, Sibei Yang, Wenping Wang, Jingyi Yu, Xuming He, Yuexin Ma
    Accepted by IJCAI, 2024

2023

  1. ddcot.jpg
    DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models
    Accepted by NeurIPS, 2023
  2. flower_bloom.gif
    Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator
    Hanzhuo Huang*Yufan Feng*Cheng Shi, Lan Xu, Jingyi Yu, Sibei Yang†
    Accepted by NeurIPS, 2023
  3. ICCV2023
  4. ICCV2023
    EdaDet: Open-Vocabulary Object Detection Using Early Dense Alignment
    Accepted by ICCV, 2023
  5. ICCV2023
    CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection
    Accepted by ICCV, 2023
  6. ICCV2023
    Temporal Collection and Distribution for Referring Video Object Segmentation
    Accepted by ICCV, 2023
  7. ICCV2023
    Grounded lmage Text Matching with Mismatched Relation Reasoning
    Yu Wu*, Yana Wei*, Haozhe Wang, Yongfei Liu, Sibei Yang, Xuming He†
    Accepted by ICCV, 2023
  8. CVPR2023
    Contrastive Grouping with Transformer for Referring Image Segmentation
    Accepted by CVPR, 2023
  9. AAAI2023
    CCQ: Cross-Class Query Network for Partially Labeled Organ Segmentation
    Xuyang Liu, Bingbing Wen, and Sibei Yang†
    Accepted by AAAI, 2023
  10. SIGGRAPH2023
    DreamFace: Progressive Generation of Animatable 3D Faces under Text Guidance
    Longwen Zhang*, Qiwei Qiu*, Hongyang Lin*, Qixuan Zhang, Cheng Shi, Wei Yang, Ye Shi, Sibei Yang†, Lan Xu†, Jingyi Yu†
    Accepted by SIGGRAPH, 2023
  11. TPAMI2023
    A Unified Visual Information Preservation Framework for Self-supervised Pre-training in Medical Image Analysis
    Hong-Yu Zhou*, Chixiang Lu*, Chaoqi Chen, Sibei Yang, Yizhou Yu†
    Accepted by TPAMI, 2023
  12. TPAMI2023
    A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-oriented Perspective
    Chaoqi Chen*, Yushuang Wu*, Qiyuan Dai*, Hong-Yu Zhou*, Mutian Xu, Sibei Yang†, Xiaoguang Han†, Yizhou Yu†
    Submitted to TPAMI, 2023

2022

  1. ECCV2022
    Spatial and Visual Perspective-Taking via View Rotation and Relation Reasoning for Embodied Reference Understanding
    Accepted by ECCV, 2022

Teaching

CS181: Artificial Intelligence I (Spring 2022, Spring 2023, Spring 2024)

CS282: Machine Learning (Fall 2021, Fall 2022, Fall 2023)