Yu Li (李昱)

Principal Researcher

International Digital Economy Academy (IDEA)

Guangdong-HongKong-Macau Greater Bay Area

Shenzhen, China

I am currently a Principal Researcher at IDEA, where I lead two research groups: one focusing on AI-Generated Content and the other exploring AI for Science. I am passionate about building AI systems for content generation and scientific discovery.

Group GitHub Pixel-Talk Computer Vision IDEA-XL AI4Science
Yu Li

Research Highlights

Recognized in Stanford University's World's Top 2% Scientists list, 2020-2025.
Leading AI4Science work on generative and predictive models and AI agents for drug discovery.
Building human-centric video understanding and generation models to support embodied AI.
Contributed AI technologies to widely used products including DaVinci Resolve, QQ, VOZO.ai, and PatSight.

Professional Services

(Lead) Area Chair

  • CVPR 2023-2026, ECCV 2024
  • NeurIPS 2023-2025, ICML 2025-2026, ICLR 2025

Adjunct Faculty

  • Adjunct Professor at SCUT
  • Adjunct Associate Professor at CUHK(SZ)

Program Chair / Organizer

  • 1-4th PBDL Workshop (in conjunction with ICCV'17-21, CVPR'24)

Guest Editor

  • IJCV Special Issue on Physics Based Vision meets Deep Learning

Recent News

Selected Publications

DiffSHEG
DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation
Junming Chen, Yunfei Liu, Jianan Wang, Ailing Zeng, Yu Li, Qifeng Chen
CVPR 2024
Website
DWPose
DWPose: Effective Whole-body Pose Estimation with Two-stages Distillation
Zhendong Yang, Ailing Zeng, Chun Yuan, Yu Li
ICCV 2023, CV4Metaverse Workshop
Code
OSX
OSX: One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer
Jing Lin, Ailing Zeng, Haoqian Wang, Lei Zhang, Yu Li
CVPR 2023 Top 1 on AGORA
Project
CT2
CT^2: Colorization Transformer via Color Tokens
Shuchen Weng, Jimeng Sun, Yu Li, Si Li, Boxin Shi
ECCV 2022 Oral
Code PDF
Hybrid Warping
Hybrid Warping Fusion for Video Frame Interpolation
Yu Li*, Ye Zhu*, Ruoteng Li, Xintao Wang, Yue Luo, Ying Shan
IJCV 2022
Link
TeViT
TeViT: Temporally Efficient Vision Transformer for Video Instance Segmentation
Shusheng Yang, Xinggang Wang, Yu Li, Yuxin Fang, Jiemin Fang, Wenyu Liu, Xun Zhao, Ying Shan
CVPR 2022 Oral
Code PDF
QueryInst
QueryInst: Instances as Queries
Yuxin Fang*, Shusheng Yang*, Xinggang Wang, Yu Li, Chen Fang, Ying Shan, Bin Feng, Wenyu Liu
ICCV 2021
Code PDF Demo
GFP-GAN
GFP-GAN: Towards Real-World Blind Face Restoration with Generative Facial Prior
Xintao Wang, Yu Li, Honglun Zhang, Ying Shan
CVPR 2021
Code PDF Website
Low Light Video
Learning Temporal Consistency for Low Light Video Enhancement from Single Images
Fan Zhang, Yu Li, Shaodi You, Ying Fu
CVPR 2021
Code PDF
Fast VOS
Fast Video Object Segmentation using the Global Context Module
Yu Li*, Zhuoran Shen*, Ying Shan
ECCV 2020
PDF
Intrinsic Image
Unsupervised Learning for Intrinsic Image Decomposition from a Single Image
Yunfei Liu, Yu Li, Shaodi You, Feng Lu
CVPR 2020
PDF
Image Filtering
Mutually Guided Image Filtering
Xiaojie Guo, Yu Li, Jiayi Ma, Haibin Ling
ACM MM 2017 & T-PAMI 2018
Link
LIME
LIME: Low-light Image Enhancement via Illumination Map Estimation
Xiaojie Guo, Yu Li, Haibin Ling
T-IP 2016
Link
PatchMatch Filter
PatchMatch Filter: Edge-Aware Filtering Meets Randomized Search for Correspondence Field Estimation
Jiangbo Lu, Yu Li, Hongsheng Yang, Dongbo Min, Weiyong Eng, Minh N. Do
T-PAMI 2016
Link
Fast Guided Interpolation
Fast Guided Global Interpolation for Depth and Motion
Yu Li, Dongbo Min, Minh N. Do, Jiangbo Lu
ECCV 2016 Spotlight
Project
SPM-BP
SPM-BP: Sped-up PatchMatch Belief Propagation for Continuous MRFs
Yu Li, Dongbo Min, Michael S. Brown, Minh N. Do, Jiangbo Lu
ICCV 2015 Oral
Project
Layer Separation
Single Image Layer Separation using Relative Smoothness
Yu Li, Michael S. Brown
CVPR 2014 Oral
PDF Code
BioMD: All-atom Generative Model for Biomolecular Dynamics Simulation
Bin Feng, Jiying Zhang, Xinni Zhang, Zijing Liu, Yu Li
ICLR 2026
OpenReview arXiv
LigUnity
A Foundation Model for Protein-Ligand Affinity Prediction through Jointly Optimizing Virtual Screening and Hit-to-Lead Optimization
Bin Feng, Zijing Liu, Mingjun Yang, Junjie Zou, He Cao, Yu Li, Lei Zhang, Sheng Wang
(Cell) Patterns, 2025 Cover Article
Link Preprint Code
Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations
Hao Li, He Cao, Bin Feng, Yanjun Shao, Xiangru Tang, Zhiyuan Yan, Li Yuan, Yonghong Tian, Yu Li
NeurIPS 2025 Chemical Reasoning
arXiv Code
Rethinking Text-based Protein Understanding: Retrieval or LLM?
Juntong Wu, Zijing Liu, He Cao, Hao Li, Bin Feng, Zishan Shu, Ke Yu, Li Yuan, Yu Li
EMNLP 2025 Oral
ACL arXiv Code
InstructMol
InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery
He Cao, Zijing Liu, Xingyu Lu, Yuan Yao, Yu Li
COLING 2025
ACL Code
Towards Stable Representations for Protein Interface Prediction
Ziqi Gao, Zijing Liu, Yu Li, Jia Li
NeurIPS 2024
OpenReview
SubgDiff: A Subgraph Diffusion Model to Improve Molecular Representation Learning
Jiying Zhang, Zijing Liu, Yu Wang, Bin Feng, Yu Li
NeurIPS 2024
Proceedings Code
Protein Multimer Structure Prediction via Prompt Learning
Ziqi Gao, Xiangguo Sun, Zijing Liu, Yu Li, Hong Cheng, Jia Li
ICLR 2024 Spotlight
OpenReview