Shaohui Li

Shaohui Li

ZJU100 Young Professor Ph.D. Supervisor

Biography

Shaohui Li (李劭辉) is a ZJU100 Young Professor (Hundred Talents Program Research Fellow) and Ph.D. Supervisor at the College of Information Science & Electronic Engineering, Zhejiang University. His research interests mainly include video and image coding, signal processing, and multi-agent systems. Currently, he is leading a National Natural Science Foundation of China (NSFC) Young Scientists Fund project and has participated in multiple major and key NSFC projects. He has received honors such as the Second Prize for Technological Invention from the Chinese Institute of Electronics and the First Prize for Science and Technology Progress from Shanghai Municipality. He was also selected for the 2023 Postdoctoral Innovative Talent Support Program. He has published over 40 papers in relevant journals and conferences including IEEE TSP, IEEE TCSVT, ICLR, ICML, ECCV, etc., and holds over 10 authorized invention patents (including 2 US patents). He co-authored the monograph Frontier of Artificial Intelligence Development (人工智能发展前沿).

Research Interests

  • Deep Learning & Signal Processing
    data-driven nonlinear transforms, learnable filter banks / invertible transforms\
  • Video and Image Coding
    AI Codec, progressive coding, lossless coding, coding for machine intelligence
  • Multi-Agent Systems
    communication, perception, planning, decision-making, simulation (physics-based simulation & world models)

Join My Team / Opportunities

I am always looking for motivated students and researchers to join my team.

  1. Prospective Ph.D. Students (2027 Cohort): I welcome applications for the 2027 Ph.D. program. Interested candidates are welcome to contact me to discuss your background and research interests.
  2. Research Interns: Research opportunities are available for highly motivated undergraduate students interested in my research areas.
  3. Postdoctoral Fellows & Research Engineers: I am continuously recruiting Postdocs and Research Engineers. Colleagues interested in collaboration are strongly encouraged to contact me.
  4. Contact: Please send your CV and a statement of your research interests to: lishaohui@zju.edu.cn

Working Experience

  • Zhejiang University, College of Information Science & Electronic Engineering, ZJU100 Young Professor, Ph.D. Supervisor, Sept. 2025 - Present
  • Tsinghua University, Postdoctoral Fellow in Computer Science and Technology, 2022 - 2025

Education

  • Ph.D.: Shanghai Jiao Tong University, Information and Communication Engineering, 2022 (Supervisor: Prof. Hongkai Xiong)
  • M.S.: Shanghai Jiao Tong University, Information and Communication Engineering, 2019 (Supervisor: Prof. Hongkai Xiong)
  • B.Eng.: Dalian University of Technology, Electronic Information Engineering, 2016

Publications

I. Journal Papers

  • Shaohui Li, Wenrui Dai*, Ziyang Zheng, Chenglin Li, Junni Zou, Hongkai Xiong. “Reversible Autoencoder: A CNN-based Nonlinear Lifting Scheme for Image Reconstruction.” IEEE Transactions on Signal Processing (TSP), vol. 69, pp. 3117-3131, June 2021. (JCR Q1, IF=5.8)
  • Shaohui Li, Han Li, Wenrui Dai*, Chenglin Li, Junni Zou, Hongkai Xiong. “Learned Progressive Image Compression with Dead-Zone Quantizers.” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. 33, no. 6, pp. 2962-2978, June 2023. (JCR Q1, IF=11.1)
  • Shaohui Li, Wenrui Dai, Yimian Fang, Ziyang Zheng, Wen Fei, Hongkai Xiong*. “Revisiting Learned Image Compression With Statistical Measurement of Latent Representations.” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. 34, no. 4, pp. 2891-2907, Apr. 2024. (JCR Q1, IF=11.1)
  • Shaohui Li, Shuoyu Ma, Wenrui Dai*, Nuowen Kan, Fan Cheng, Chenglin Li, Junni Zou, Hongkai Xiong. “Task-Adapted Learnable Embedded Quantization for Scalable Human-Machine Image Compression.” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. 35, no. 5, pp. 4768-4783, May 2025. (JCR Q1, IF=11.1)
  • Shaohui Li, Wenrui Dai*, Nuowen Kan, Chenglin Li, Junni Zou, Hongkai Xiong. “Learnable Non-uniform Quantization With Sampling-based Optimization for Variable-Rate Learned Image Compression.” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. 35, no. 8, pp. 8314-8329, Aug. 2025. (JCR Q1, IF=11.1)
  • Xin Li, Shaohui Li*, Wenrui Dai*, Han Li, Nuowen Kan, Chenglin Li, Junni Zou, Hongkai Xiong. “Point Cloud Attribute Compression With Geometry-Aware Lifting-Based Multiscale Networks.” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Early Access, 2025. DOI: 10.1109/TCSVT.2025.3597448. (JCR Q1, IF=11.1)
  • Maida Cao, Wenrui Dai*, Shaohui Li*, Chenglin Li, Junni Zou, Ying Chen, Hongkai Xiong. “Generative Probabilistic Entropy Modeling with Conditional Diffusion for Learned Image Compression.” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. 35, no. 9, pp. 9443-9459, Sept. 2025. (JCR Q1, IF=11.1)
  • Yuxin Ke, Shaohui Li, Zhi Li, Haoran Li, Yu Liu*, You He. “ArenaSim: A High-Performance Simulation Platform for Multi-Robot Self-Play Learning.” IEEE Robotics and Automation Letters (RAL), vol. 10, no. 6, pp.5497-5504, June 2025. (JCR Q1, IF=5.3)
  • Xin Li, Wenrui Dai*, Shaohui Li, Chenglin Li, Junni Zou, Hongkai Xiong*. “3-D Point Cloud Attribute Compression with $p$-Laplacian Embedding Graph Dictionary Learning.” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 46, no. 2, pp. 975-993, Feb. 2024. (JCR Q1, IF=18.6)
  • Maida Cao, Wenrui Dai*, Shaohui Li, Chenglin Li, Junni Zou, Ying Chen, Hongkai Xiong. “End-to-End Optimized Image Compression with Deep Gaussian Process Regression.” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Early Access, 2022. DOI: 10.1109/TCSVT.2022.3209661 (JCR Q1, IF=11.1)
  • Yuehan Xiong, Wenrui Dai*, Wen Fei, Shaohui Li, Hongkai Xiong*. “Anisotropic Spherical Scattering Networks via Directional Spin Wavelet.” IEEE Transactions on Signal Processing (TSP), vol. 71, pp. 2981-2996, Aug. 2023. (JCR Q1, IF=5.8)
  • Lisha Wang, Chenglin Li*, Wenrui Dai, Shaohui Li, Junni Zou, Hongkai Xiong. “QoE-Driven Adaptive Streaming for Point Clouds.” IEEE Transactions on Multimedia (TMM), vol. 25, pp. 2543-2558, Feb. 2023. (JCR Q1, IF=9.7)
  • Baihui Xiao, Shulan Ruan*, Zhi Li, Shaohui Li, Yu Liu, Xiu Li, You He. “Improving Radar–Camera Fusion for 3D Object Detection via Eliciting Knowledge From Foundation Model.” IEEE/ASME Transactions on Mechatronics (TMech), Early Access, 2025. DOI: 10.1109/TMECH.2025.3584379. (JCR Q1, IF=7.3)
  • Huajie Wang, Zhi Li, Shaohui Li, Yu Liu*, You He. “Unfolding Sample-Level Difficulty for Adaptive Pseudo-Labeling in Semi-Supervised Learning.” Chinese Journal of Electronics (CJE), vol. 35, no.2, pp. 1-14, 2026. DOI: 10.23919/cje.2025.00.128.
  • You He, Shulan Ruan*, Dong Wang*, Huchuan Lu, Zhi Li, Yang Liu, Xu Chen, Shaohui Li, Jie Zhao, Jiaxuan Liang. “Intelligent Decision-Making Driven by Large AI Models: Progress, Challenges and Prospects.” CAAI Transactions on Intelligence Technology (CIT), Early Access, 2025. DOI: 10.1049/cit2.70084.
  • Hao Dong, Shaohui Li, Nuowen Kan, Ziyang Zheng, Wenrui Dai, Hongkai Xiong. “Research on Joint Source-Channel Coding Method Based on Deep Compressed Sensing.” Acta Electronica Sinica. Accepted, 2025.

II. Conference Papers

  • Shaohui Li, Ziyang Zheng, Wenrui Dai, Hongkai Xiong. “Lossy Image Compression with Filter Bank Based Convolutional Networks.” IEEE Data Compression Conference (DCC’2019), Snowbird, UT, USA, pp. 23-32, Mar. 26-29, 2019. (Oral)
  • Shaohui Li, Ziyang Zheng, Wenrui Dai*, Junni Zou, Hongkai Xiong. “Rev-AE: A Learned Frame Set for Image Reconstruction.” IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP’2020), Barcelona, Spain, pp. 1823-1827, May 4-8, 2020. (Lecture)
  • Hao Dong, Nuowen Kan*, Wenrui Dai*, Shaohui Li, Ziyang Zheng, Chenglin Li, Junni Zou, Hongkai Xiong. “Error-Resilient Learned Video Compression With Channel Importance-Aware Redundancy Allocation.” IEEE Data Compression Conference (DCC’2026), Snowbird, Utah, USA, Mar. 24-27, 2026.
  • Shuoyu Ma, Wenrui Dai*, Maida Cao, Shaohui Li, Ziyang Zheng, Chenglin Li, Junni Zou, Hongkai Xiong. “Pushing Bit-Width Limits in LLM Quantization With Saliency-Guided Mix-Precision Allocation and Learnable Affine Transformation.” IEEE Data Compression Conference (DCC’2026), Snowbird, Utah, USA, Mar. 24-27, 2026.
  • Haolin Luan, Shuoyu Ma, Shaohui Li*, Wenrui Dai, Nuowen Kan, Chenglin Li, Junni Zou, Hongkai Xiong. “Efficient Conditional Entropy Coding for Learned Progressive Image and Video Compression.” IEEE International Conference on Visual Communications and Image Processing (VCIP 2025), Klagenfurt, Austria, Dec. 1-4, 2025.
  • Han Li, Shaohui Li*, Wenrui Dai*, Maida Cao, Nuowen Kan, Chenglin Li, Junni Zou, Hongkai Xiong. “On Disentangled Training for Nonlinear Transform in Learned Image Compression.” International Conference on Learning Representations (ICLR 2025), Singapore, Apr. 24-28, 2025. (Spotlight, TOP)
  • Han Li, Shaohui Li*, Wenrui Dai*, Chenglin Li, Junni Zou, Hongkai Xiong. “Frequency-Aware Transformer for Learned Image Compression.” International Conference on Learning Representations (ICLR 2024), Vienna, Austria, May 7-11, 2024. (TOP)
  • Han Li, Shaohui Li*, Shuangrui Ding, Wenrui Dai*, Maida Cao, Chenglin Li, Junni Zou, Hongkai Xiong. “Image Compression for Machine and Human Vision with Spatial-Frequency Adaptation.” European Conference on Computer Vision (ECCV 2024), Milan, Italy, pp. 382-399, Sept. 29-Oct. 4, 2024. (TOP)
  • Yuankun Zeng, Shaohui Li, Zhi Li, Shulan Ruan, Yu Liu*, You He. “Communication-Efficient Collaborative Perception with Semantic and Statistical Compression.” Chinese Conference on Pattern Recognition and Computer Vision (PRCV 2025), Shanghai, China, Oct. 16-19, 2025.
  • Yilin Jin, Shaohui Li, Zhi Li, Yu Liu*. “Low-Resolution Hierarchical Training for Efficient 3D Gaussian Splatting.” IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP’2025), Hyderabad, India, Apr. 6-11, 2025.
  • Wenpeng Zhang, Shaohui Li, Lanfeng Wang, Yu Liu*. “Efficient Multi-Agent Reinforcement Learning for Pursuit-Evasion Game of Unmanned Surface Vessels with a Faster Evader.” International Conference on Robotics, Control and Automation (ICRCA 2025), Shanghai, China, Mar. 7-9, 2025.
  • Nantian He, Shaohui Li, Zhi Li, Yu Liu*, You He. “ReDiffuser: Reliable Decision-Making Using a Diffuser with Confidence Estimation.” International Conference on Machine Learning (ICML 2024), Vienna, Austria, pp. 17921-17933, July 21-27, 2024. (TOP)
  • Weibo Jiang, Shaohui Li, Zhi Li, Yuxin Ke, Zhizhuo Jiang, Yaowen Li, Yu Liu*. “Dual-Policy-Guided Offline Reinforcement Learning with Optimal Stopping.” International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2024), Auckland, New Zealand, pp. 2315-2317, May 6-10, 2024.
  • Wenxin Tian, Shaohui Li, Wenrui Dai*, Cewu Lu, Weisheng Hu, Lin Zhang, Junfeng Du, Hongkai Xiong. “Learned Progressive Image Compression With Spatial Autoregression.” IEEE International Conference on Visual Communications and Image Processing (VCIP 2023), Jeju, Korea, Republic of, Dec. 4-7, 2023. (Oral)
  • Rulin Huang, Shaohui Li, Wenrui Dai*, Chenglin Li, Junni Zou, Hongkai Xiong. “Improving Optical Flow Inference for Video Colorization.” IEEE International Symposium on Circuits and Systems (ISCAS 2022), Austin, TX, USA, pp. 3185-3189, May 28 - June 1, 2022.
  • Rulin Huang, Shaohui Li, Wenrui Dai*, Jixiang Luo, Chenglin Li, Junni Zou, Hongkai Xiong. “Video Compression via Inter-frame Chroma Prediction.” IEEE Data Compression Conference (DCC’2022), Snowbird, Utah, USA, pp. 457-457, Mar. 22-24, 2022.
  • Liewen Liao, Shaohui Li, Jixiang Luo, Wenrui Dai*, Chenglin Li, Junni Zou, Hongkai Xiong. “Efficient Decoder for Learned Image Compression via Structured Pruning.” IEEE Data Compression Conference (DCC’2022), Snowbird, Utah, USA, pp. 464-464, Mar. 22-24, 2022.
  • Jixiang Luo, Shaohui Li, Wenrui Dai*, De Cheng, Gang Li, Chenglin Li, Junni Zou, Hongkai Xiong. “Lossless Compression for Video Streams with Frequency Prediction and Macro Block Merging.” IEEE Data Compression Conference (DCC’2021), Snowbird, UT, USA, pp. 353-353, Mar. 23-26, 2021.
  • Jixiang Luo, Shaohui Li, Wenrui Dai*, Yuhui Xu, De Cheng, Gang Li, Hongkai Xiong. “Noise-to-Compression Variational Autoencoder for Efficient End-to-End Optimized Image Coding.” IEEE Data Compression Conference (DCC’2020), Snowbird, UT, USA, pp.33-42, Mar. 24-27, 2020. (Oral)
  • Maida Cao, Wenrui Dai*, Shaohui Li, Han Li, Chenglin Li, Junni Zou, Hongkai Xiong. “Entropy Relaxed Lattice Vector Quantization for Learned Image Compression.” IEEE Data Compression Conference (DCC’2024), Snowbird, UT, USA, pp. 548-548, Mar. 19-22, 2024.
  • Danxu Li, Zhi Li*, Shaohui Li, Huajie Wang, Yu Liu*. “Formation Navigation with Relative Distance Maintenance in Obstacle Environments.” First Aerospace Frontiers Conference (AFC 2024), Xi’an, China, April 2024. (Oral)
  • Ning Gong, Zhi Li, Shaohui Li, Yuxin Ke, Zhizhuo Jiang, Yaowen Li, Yu Liu*. “Multi-agent Perception via Co-attentive Communication Mechanism.” Chinese Conference on Pattern Recognition and Computer Vision (PRCV 2023), Xiamen, China, pp. 409-421, Oct. 13-15, 2023.
  • Yimian Fang, Wen Fei, Shaohui Li, Wenrui Dai*, Chenglin Li, Junni Zou, Hongkai Xiong. “Fully Integerized End-to-End Learned Image Compression.” IEEE Data Compression Conference (DCC’2023), Snowbird, UT, USA, pp. 337-337, Mar. 21-24, 2023.
  • Xin Li, Wenrui Dai*, Shaohui Li, Chenglin Li, Junni Zou, Hongkai Xiong. “Graph Dictionary Learning for 3-D Point Cloud Compression.” IEEE Data Compression Conference (DCC’2022), Snowbird, Utah, USA, pp. 463-463, Mar. 22-24, 2022.
  • Maida Cao, Wenrui Dai, Shaohui Li, Chenglin Li, Junni Zou, Ying Chen, Hongkai Xiong. “Entropy Modeling via Gaussian Process Regression for Learned Image Compression.” IEEE Data Compression Conference (DCC’2022), Snowbird, Utah, USA, pp. 163-172, Mar. 22-24, 2022. (Oral)
  • Liang Yuan, Jixiang Luo, Shaohui Li, Wenrui Dai*, Chenglin Li, Junni Zou, Hongkai Xiong. “Learned Image Compression with Channel-Wise Grouped Context Modeling.” IEEE International Conference on Image Processing (ICIP 2021), Anchorage, Alaska, USA, pp. 2099-2103, Sept. 19-22, 2021.
  • Ziyang Zheng, Shanghong Wang, Shaohui Li, Wenrui Dai*, Junni Zou, Feifei Li, and Hongkai Xiong. “DSCR-Net: A Diffractive Sensing and Complex-Valued Reconstruction Network for Compressive Sensing.” IEEE International Symposium on Circuits and Systems (ISCAS 2020), Sevilla, Spain, pp. 1-5, Oct. 10-21, 2020.
  • Shixin Hong, Yu Liu*, Zhi Li, Shaohui Li, You He. “Multi-agent Collaborative Perception via Motion-aware Robust Communication Network.” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024), Seattle, USA, pp. 15301-15310, Jun. 17-21, 2024. (TOP)
  • Runqi Yang, Yu Liu*, Zhi Li, Shaohui Li, Likang Wu. “Rethinking Offline Reinforcement Learning for Sequential Recommendation from A Pair-Wise Q-Learning Perspective.” International Joint Conference on Neural Networks (IJCNN 2024), Yokohama, Japan, Jun. 30-Jul. 5, 2024.

III. Books

  • You He, Huchuan Lu, Dong Wang, Zheng Li, Xu Chen, Shaohui Li. “Frontiers of Artificial Intelligence Development.” Beijing: Tsinghua University Press, October 2025. (JD Link)