CHU Xiaowen (褚晓文)
Professor, Data Science and Analytics Thrust and Artificial Intelligence Thrust
Acting Head, Artificial Intelligence Thrust
Information Hub
The Hong Kong University of Science and Technology (Guangzhou)
Email: xwchu@hkust-gz.edu.cn (or xwchu@ust.hk)
Dr. Chu received his B.Eng. degree in Computer Science from Tsinghua University, Beijing, P. R. China, in 1999, and the Ph.D. degree in Computer Science from The Hong Kong University of Science and Technology in 2003. He is currently a Professor at the Data Science and Analytics Thrust and Artificial Intelligence Thrust, Information Hub of HKUST(GZ), and an Affiliate Professor of The Hong Kong University of Science and Technology. He is the Acting Head of the Artificial Intelligence Thrust, and has been the Acting Head and Head of the Data Science and Analytics Thrust during 2023-25. He has been working at the Department of Computer Science, Hong Kong Baptist University during 2003-2021. He was a vice-chairman of the Blockchain Technical Committee of China Institute of Communications. His current research interests include Machine Learning Systems, GPU Computing, Embodied AI, and AI4Science. He is a Fellow of IEEE, and Fellow of AAIA.
I am looking for self-motivated Research Assistants, PhD students, and Postdoctoral Fellows who are interested to work in the following field(s):
Machine learning systems
GPU computing
Embodied AI
[19 Sept 2025] The paper "ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference" has been accepted by NeurIPS 2025. Congratulations to Mr. Xiang Liu and Dr. Zhenheng Tang, and all co-authors!
[21 Aug 2025] The paper "Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research" has been accepted by Findings of EMNLP 2025. Congratulations to Mr. Xiang Liu and Mr. Penglei Sun, and all co-authors!
[23 July 2025] The paper “Mast: Efficient Training of Mixture-of-Experts Transformers with Task Pipelining and Ordering” has received the Distinguished Paper Award of ICDCS 2025. Congratulatios to Mr. Wenxiang Lin, Mr. Xinglin Pan, and all co-authors!
[15 July 2025] The paper “Interleaved Bitstream Execution for Multi-Pattern Regex Matching on GPUs” has been accepted by MICRO 2025. Congratulatios to Mr. Tianao Ge and Dr. Hongyuan Liu!
[16 June 2025] Two papers “RA-NeRF: Robust Neural Radiance Field Reconstruction with Accurate Camera Pose Estimation under Complex Trajectories” and “SAFormer: Spatially Adaptive Transformer for Efficient and Multi-Resolution Occupancy Prediction” have been accepted by IROS 2025. Congratulatios to Qingsong Yan, Song Tang, and all co-authors!
[16 May 2025] The paper “BurstGPT: A Real-World Workload Dataset to Optimize LLM Serving Systems” has been accepted by KDD 2025 (Datasets and Benchmarks Track). Congratulatios to Dr. Yuxin Wang, Mr. Yuhan Chen, and all co-authors!
[16 May 2024] The paper “AceEdit: Advancing Continuous Knowledge Editing For Large Language Models” has been accepted by ACL 2025, and the paper "UnrealLLM: Towards Highly Controllable and Interactable 3D Scene Generation by LLM-powered Procedural Content Generation" has been accepted by ACL Findings 2025. Congratulations to Mr. Qi Li, Mr. Song Tang, and all co-authors!
[1 May 2025] The paper “Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression” has been accepted by ICML 2025. Congratulatios to Mr. Peijie Dong and all co-authors!
[1 April 2025] The paper “SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs” has received the Best Paper Award of EuroSys 2025. Congratulatios to Mr. Ruibo FAN and all co-authors!
[27 March 2025] Two papers “Mitigating Contention in Stream Multiprocessors for Pipelined Mixture of Experts: An SM-Aware Scheduling Approach” and "Mast: Efficient Training of Mixture-of-Experts Transformers with Task Pipelining and Ordering" have been accepted by ICDCS 2025. Congratulatios to Mr. Xinglin PAN and all co-authors! (104 papers were accepted out of 529 submissions)
[24 Jan 2025] The paper “SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs” has been accepted by EuroSys 2025. Congratulatios to Mr. Ruibo FAN and all co-authors! (30 papers were accepted out of 367 new submissions in this Fall Submission round)
[23 Jan 2025] Three papers got accepted by ICLR 2025: “STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs”, "Hot-pluggable Federated Learning: Bridging General and Personalized FL via Dynamic Selection", and “The Lottery LLM Hypothesis, Rethinking What Abilities Should LLM Compression Preserve?" (Blogpost Track). Congratulations to Mr. Peijie DONG, Dr. Zhenheng TANG, and all co-authors!
[10 Dec 2024] The paper “ParZC: Parametric Zero-Cost Proxies for Efficient NAS” has been accepted by AAAI 2025 and selected for oral presentation. Congratulations to Mr. Peijie DONG and all co-authors! (600 oral presentations out of 3032 accepted papers out of 12,957 submissions)
[9 Dec 2024] The paper “FSMoE: A Flexible and Scalable Training System for Sparse Mixture-of-Experts Models” has been accepted by ACM ASPLOS 2025. Congratulations to Mr. Xinglin PAN and all co-authors!
[26 Sept 2024] The paper “FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion” has been accepted by NeurIPS 2024 as a spotlight. Congratulations to Dr. Zhenheng TANG and all co-authors!
[26 Sept 2024] The paper “Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models” has been accepted by NeurIPS 2024. Congratulations to Mr. Peijie DONG and all co-authors!
[26 Sept 2024] The paper “Should We Really Edit Language Models? On the Evaluation of Edited Language Models” has been accepted by NeurIPS 2024. Congratulations to Mr. Qi LI and all co-authors!
[20 Sept 2024] Two papers “LongGenBench: Long-context Generation Benchmark” and "LPZero: Language Model Zero-cost Proxy Search from Zero" have been accepted by EMNLP Findings 2024. Congratulations to Mr. Xiang LIU and Mr. Peijie Dong and all co-authors!
[16 July 2024] The paper “3D Question Answering for City Scene Understanding” has been accepted by ACM International Conference on Multimedia 2024. Congratulations to Mr. Penglei Sun again!
[1 July 2024] The paper “Multi-Task Domain Adaptation for Language Grounding with 3D Objects” has been accepted by ECCV 2024. Congratulations to Mr. Penglei Sun!
[16 May 2024] The paper “BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation” has been accepted by ACL 2024, and the paper "Can We Continually Edit Language Models? On the Knowledge Attenuation in Sequential Model Editing" has been accepted by ACL Findings 2024. Congratulations to Mr. Dayou Du and Mr. Qi Li!
[2 May 2024] The paper “Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models” has been accepted by ICML 2024. Congratulations to Mr. Peijie Dong!
[22 March 2024] The paper “DTC-SpMM: Bridging the Gap in Accelerating General Sparse Matrix Multiplication with Tensor Cores” has been accepted by ACM ASPLOS 2024. Congratulations to Mr. Ruibo Fan!
[16 Feb 2024] The paper “FedImpro: Measuring and Improving Client Update in Federated Learning,” has been accepted by ICLR 2024. Congratulatios to Mr. Zhenheng Tang!
[8 Feb 2024] The paper “ScheMoE: An Extensible Mixture-of-Experts Distributed Training System with Tasks Scheduling” has been accepted by EuroSys 2024. Congratulatios to Prof. Shaohuai Shi and Mr. Xinglin Pan!
[20 Dec2023] The paper “Benchmarking and Dissecting the Nvidia Hopper GPU Architecture” has been accepted by IEEE IPDPS 2024. Congratulations to Mr. Weile Luo and all other authors!
[9 Dec 2023] The paper “CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning” has been accepted by AAAI 2024.
[7 Dec 2023] Two papers “Parm: Efficient Training of Large Sparsely-Activated Models with Dedicated Schedules” and "Galaxy: A Resource-Efficient Collaborative Edge AI System for In-situ Transformer Inference" have been accepted by IEEE INFOCOM 2024. Congratulations to Mr. Xinglin Pan!
[22 Nov 2023] The paper “Asteroid: Resource-Efficient Hybrid Pipeline Parallelism for Collaborative DNN Training on Heterogeneous Edge Devices” has been conditionally accepted by ACM Mobicom 2024.
[17 May 2023] The paper “Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning” has been accepted by ACM KDD 2023.
[10 April 2023] Two papers “Evaluation and Optimization of Gradient Compression for Distributed Deep Learning” and “Accelerating Distributed Deep Learning with Fine-Grained All-Reduce Pipelining” have been accepted by IEEE ICDCS 2023.
[31 March 2023] The paper “Improving Fairness in Coexisting 5G and Wi-Fi Network on Unlicensed Band with URLLC” has been accepted by IEEE/ACM IWQoS 2023.
[23 Jan 2023] The paper “Fast Sparse GPU Kernels for Accelerated Training of Graph Neural Networks” has been accepted by IEEE IPDPS 2023. Congratulations to Mr. Ruibo Fan!
[6 Dec 2022] The paper “GossipFL: A Decentralized Federated Learning Framework with Sparsified and Adaptive Communication” has been accepted by IEEE TPDS. Congratulations to Mr. Zhenheng Tang!
[2 Dec 2022] The paper “PipeMoE: Accelerating Mixture-of-Experts through Adaptive Pipelining” has been accepted by IEEE INFOCOM 2023. Congratulations to Dr. Shaohuai Shi and Mr. Xinglin Pan!
[19 Nov 2022] Two papers “Rethinking Disparity: A depth range free Multi-View Stereo based on Disparity” and "NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension" have been accepted by AAAI 2023. Congratulations to Mr. Qingsong Yan, Mr. Xin He, and all other co-authors!
[26 Sept 2022] The paper “Dissecting Mining Pools of Bitcoin Network: Measurement, Analysis and Modeling” has been accepted by IEEE TNSE. Congratulations to Mr. Canhui Wang!
[9 July 2022] Two papers “EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching” and "EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs" have been accepted by ECCV 2022. Congratulations to Dr. Qiang Wang, Mr. Xin He, and all other co-authors!
[3 June 2022] The paper “Evolutionary Multi-objective Architecture Search Framework: Application to COVID-19 3D CT Classification” has been accepted by MICCAI 2022. Congratulations to Mr. Xin He!
[21 May 2022] The paper “Energy-aware Non-preemptive Task Scheduling with Deadline Constraint in DVFS-enabled Heterogeneous Clusters” has been accepted by IEEE TPDS. Congratulations to Dr. Qiang Wang and Dr. Xinxin Mei!
[15 May 2022] The paper “Virtual Homogeneity Learning” has been accepted by ICML 2022. Congratulations to Mr. Zhenheng Tang!
[21 April 2022] The paper “Energy-efficient Online Scheduling of Transformer Inference Services on GPU Servers” has been accepted by IEEE Transactions on Green Communications and Networking. Congratulations to Mr. Yuxin Wang and Dr. Qiang Wang!
[29 March 2022] The paper “Incentive Mechanisms in Federated Learning and Game-theoretical Approach” has been accepted by IEEE Network.
[16 Nov 2021] The paper “Joint Access Point Placement and Power-Channel-Resource-Unit Assignment for IEEE 802.11ax-Based Dense WiFi Network with QoS Requirements” has been accepted by IEEE Transactions on Mobile Computing.
[14 May 2021] The paper “Exploiting Simultaneous Communications to Accelerate Data Parallel Distributed Deep Learning” has received the Best Paper Award of IEEE INFOCOM 2021. Congratulations to Dr. SHI Shaohuai and Prof. Bo Li! A preprint can be found at arXiv.
[11 April 2021] The paper “BU-Trace: A Permissionless Mobile System for Privacy-Preserving Intelligent Contact Tracing” has received the Best Paper Award of the 2021 International Workshop on Mobile Ubiquitous Systems and Technologies, collated with DASFAA 2021. Congratulations to all team members! A preprint can be found at arXiv.
[29 March 2021] The paper “P2B-Trace: Privacy-Preserving Blockchain-based Contact Tracing to Combat Pandemics” has been accepted by SIGMOD 2021. Congratulations to all team members! A preprint can be found at arXiv.
[6 March 2021] The paper “IRS: A Large Naturalistic Indoor Robotics Stereo Dataset to Train Deep Models for Disparity and Surface Normal Estimation” has been accepted by ICME 2021. Congratulations to all team members! A preprint can be found at arXiv.
[4 March 2021] The paper “EDNet: Efficient Disparity Estimation with Cost Volume Combination and Attention-based Spatial Residual” has been accepted by CVPR 2021. This work is collaborated with Tongji University. Congratulations to all team members! A preprint can be found at arXiv.
[14 Jan 2021] The paper “MG-WFBP: Merging Gradients Wisely for Efficient Communication in Distributed Deep Learning” has been accepted by IEEE TPDS. Congratulations to Dr. SHI Shaohuai!
[26 Dec 2020] The paper “VFChain: Enabling Verifiable and Auditable Federated Learning via Blockchain Systems” has been accepted by IEEE Transactions on Network Science and Engineering. Congratulations to Dr. PNEG Zhe!
[5 Dec 2020] The paper “Exploiting Simultaneous Communications to Accelerate Data Parallel Distributed Deep Learning” has been accepted by IEEE INFOCOM 2021. Congratulations to Dr. SHI Shaohuai!
[2 Dec 2020] The paper “Automated Model Design and Benchmarking of Deep Learning Models for COVID-19 Detection with Chest CT Scans” has been accepted by AAAI 2021. Congratulations to Mr. HE Xin, Mr. WANG Shihao and all the co-authors!
[23 Nov 2020] The paper “AutoML: A Survey of the State-of-the-Art” has been accepted by Knowledge-Based Systems. Congratulations to Mr. HE Xin! Paper available on this link before Jan 29, 2021.
[11 Nov 2020] The paper “Energy-Efficient Inference Service of Transformer-Based Deep Learning Models on GPUs” has received the Best Paper Award of IEEE GreenCom 2020. Congratulations to WANG Yuxin and Dr. WANG Qiang!
[25 Oct 2020] We are organizing the Special Issue on Interplay Between Machine Learning and Networking Systems, IEEE Network [CFP]. Submission Deadline: 15 April 2021.
[21 Oct 2020] The paper “A Quantitative Survey of Communication Optimizations in Distributed Deep Learning” has been accepted by IEEE Network. Congratulations to Dr. SHI Shaohuai and all the co-authors!
[Preprint]
[19 June 2020] We are organizing the Special Issue on Communication-Efficient Distributed Machine Learning, IEEE Transactions on Network Science and Engineering [CFP]. Submission Deadline: 1 Dec 2020.
[14 June 2020] The paper “GPGPU Performance Estimation with Core and Memory Frequency Scaling” has been accepted by IEEE TPDS. Congratulations to WANG Qiang!
[2 June 2020] I am serving as a General Chair of IEEE DSS-2020 (IEEE Conference on Data Science and Systems) [CFP]. Submission Deadline: 1 Sept. 2020.
[3 April 2020] We are organizing the Special Section on Opportunities and Challenges to Integrate AI and Big Data, IEEE Transactions on Industrial Informatics [CFP]. Submission Deadline: 30 July 2020.
[22 March 2020] The paper “ESetStore: an Erasure-coded Storage System with Fast Data Recovery” has been accepted by IEEE TPDS. Congratulations to LIU Chengjian and WANG Qiang!
[13 March 2020] The paper “FMore: An Incentive Scheme of Multi-dimensional Auction for Federated Learning in MEC” collaborated with Prof. ZENG Rongfei of Northeastern University has been accepted by IEEE ICDCS 2020.
[22 January 2020] The paper “FADNet: A Fast and Accurate Network for Disparity Estimation” has been accepted by IEEE ICRA 2020. Congratulations to WANG Qiang, SHI Shaohuai, ZHENG Shizhen, and ZHAO Kaiyong!
[15 January 2020] The paper “Layer-wise Adaptive Gradient Sparsification for Distributed Deep Learning with Convergence Guarantees” has been accepted by ECAI 2020. Congratulations to SHI Shaohuai, TANG Zhenheng, WANG Qiang, and ZHAO Kaiyong!