About Me
I am a Scientist at Nex-AGI. Check Nex-AGI to explore the Nexus of Agentic Intelligence, focusing on end-to-end agent solutions ranging from Models and Data to Frameworks.
I obtained my Ph.D. degree from The University of Hong Kong (HKU) in 2020, advised by Prof. Francis C.M. Lau. Before that, I received my B.Eng in Electronic and Information Engineering from the University of Electronic Science and Technology of China (UESTC) in 2014.
My current research interests focus on LLM Agents (e.g., Agent RL, Agentic Context Engineering, and Software 3.0). We are finding ways to unleash the power of LLM in real productivity, especially to teach LLM to understand how domain experts solve problems.
Selected Publications
* Corresponding Author
+ Student Advised
Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction
Nex-AGI Team
RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
Best Paper
Di Liu, Meng Chen, Baotong Lu, Huiqiang Jiang, Zhenhua Han, Qianxi Zhang, Qi Chen, Chengruidong Zhang, Bailu Ding, Kai Zhang, Chen Chen, Fan Yang, Yuqing Yang, Lili Qiu
Minference 1.0: Accelerating pre-filling for long-context LLMs via dynamic sparse attention
Huiqiang Jiang, Yucheng Li, Chengruidong Zhang, Qianhui Wu, Xufang Luo, Surin Ahn, Zhenhua Han, Amir Abdi, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, Lili Qiu
Parrot: Efficient Serving of LLM-based Applications with Semantic Variable
Chaofan Lin+, Zhenhua Han*, Chengruidong Zhang, Yuqing Yang, Fan Yang, Chen Chen, Lili Qiu
PIT: Optimization of Dynamic Sparse Deep Learning Models via Permutation Invariant Transformation
Ningxin Zheng, Huiqiang Jiang, Quanlu Zhang*, Zhenhua Han*, Lingxiao Ma, Yuqing Yang*, Fan Yang, Chengruidong Zhang, Lili Qiu, Mao Yang, Lidong Zhou
ACM SOSP 2023
Conference
Optimizing Dynamic Neural Networks with Brainstorm
Weihao Cui+, Zhenhua Han, Lingji Ouyang+, Yichuan Wang, Ningxin Zheng, Lingxiao Ma, Yuqing Yang, Fan Yang, Jilong Xue, Lili Qiu, Lidong Zhou, Quan Chen, Haisheng Tan, Minyi Guo
USENIX OSDI 2023
Conference
Dynamic Resource Allocation for Deep Learning Clusters with Separated Compute and Storage
Mingxia Li+, Zhenhua Han, Chi Zhang, Ruiting Zhou, Yuanchi Liu, Haisheng Tan
IEEE INFOCOM 2023
ElasticFlow: An Elastic Serverless Training Platform for Distributed Deep Learning
Diandian Gu, Yihao Zhao, Yinmin Zhong, Yifan Xiong, Zhenhua Han, Peng Cheng, Fan Yang, Gang Huang, Xin Jin, Xuanzhe Liu
ASPLOS 2023
SiloD: A Co-design of Caching and Scheduling for Deep Learning Clusters
Hanyu Zhao*, Zhenhua Han*, Zhi Yang, Quanlu Zhang, Mingxia Li+, Fan Yang, Qianxi Zhang, Binyang Li, Yuqing Yang, Lili Qiu, Lintao Zhang, Lidong Zhou
EuroSys 2023
Paper
PilotFish: Harvesting Free Cycles of Cloud Gaming with Deep Learning Training
Wei Zhang+, Binghao Chen, Zhenhua Han, Quan Chen, Peng Cheng, Fan Yang, Ran Shu, Yuqing Yan, Minyi Guo
HiveD: Sharing a GPU Cluster for Deep Learning with Guarantees
Hanyu Zhao*, Zhenhua Han*, Zhi Yang, Quanlu Zhang, Fan Yang, Lidong Zhou, Mao Yang, Francis C.M. Lau, Yuqi Wang, Yifan Xiong, Bin Wang
Retiarii: A Deep Learning Exploratory-Training Framework
Quanlu Zhang, Zhenhua Han, Fan Yang, Yuge Zhang, Zhe Liu, Mao Yang, Lidong Zhou
USENIX OSDI 2020
Code
Automating Cloud Deployment for Deep Learning Inference of Real-time Online Services
Yang Li*, Zhenhua Han*, Quanlu Zhang, Zhenhua Li, Haisheng Tan
IEEE INFOCOM 2020 / IEEE/ACM ToN 2023
Gandiva: Introspective Cluster Scheduling for Deep Learning
Wencong Xiao, Romil Bhardwaj, Ramachandran Ramjee, Muthian Sivathanu, Nipun Kwatra, Zhenhua Han, Pratyush Patel, Xuan Peng, Hanyu Zhao, Quanlu Zhang, Fan Yang, Lidong Zhou
USENIX OSDI 2018
Paper
Online File Caching in Latency-Sensitive Systems with Delayed Hits and Bypassing
Chi Zhang, Haisheng Tan, Guopeng Li, Zhenhua Han, Shaofeng H-C. Jiang, Xiang-Yang Li
IEEE INFOCOM 2022
Regularization-Based Coflow Scheduling in Optical Circuit Switches
Haisheng Tan, Chi Zhang, Chao Xu, Yupeng Li, Zhenhua Han, Xiang-Yang Li
IEEE/ACM ToN 2021
Online Dispatching and Scheduling of Jobs with Heterogeneous Utilities in Edge Computing
Chi Zhang, Haisheng Tan, Haoqiang Huang, Zhenhua Han, Shaofeng H.-C. Jiang, Nikolaos Freris, Xiang-Yang Li
ACM MobiHoc 2020
Scheduling Placement-Sensitive BSP Jobs with Inaccurate Execution Time Estimation
Zhenhua Han, Haisheng Tan, Shaofeng H.-C. Jiang, Xiaoming Fu, Wanli Cao, Francis C.M. Lau
IEEE/ACM ToN 2021 (INFOCOM 2020)
OnDisc: Online Latency-Sensitive Job Dispatching and Scheduling in Heterogeneous Edge-Clouds
Zhenhua Han, Haisheng Tan, Xiang-Yang Li, Shaofeng H.-C. Jiang, Yupeng Li, Francis C.M. Lau
IEEE/ACM ToN 2019 (INFOCOM 2017)
Joint Online Coflow Routing and Scheduling in Data Center Networks
Haisheng Tan, Shaofeng Jiang, Yupeng Li, Xiang-Yang Li, Chenzi Zhang, Zhenhua Han, Francis C.M. Lau
IEEE/ACM ToN 2019
Camul: Online Caching on Multiple Caches with Relaying and Bypassing
Haisheng Tan, Shaofeng Jiang, Zhenhua Han*, Liuyan Liu, Kai Han, Qinglin Zhao
IEEE INFOCOM 2019
Energy Efficient Dynamic Virtual Machine Management in Data Centers
Zhenhua Han, Haisheng Tan, Rui Wang, Guihai Chen, Yupeng Li, Francis C.M. Lau
IEEE/ACM ToN 2019 (INFOCOM 2016)
Efficient Online Learning Based Cross-Tier Uplink Scheduling in HetNets
Zhenhua Han, Haisheng Tan, Rui Wang, Shaojie Tang, Francis C.M. Lau
IEEE/ACM ToN 2022 (INFOCOM 2018)
Congestion Game with Agent and Resource Failures
Yupeng Li, Yongzheng Jia, Haisheng Tan, Rui Wang, Zhenhua Han, Francis C.M. Lau
IEEE JSAC 2017
Professional Services
Program Committee
- • IEEE INFOCOM 2021, 2022
- • MSN 2020
Journal Reviewer
- • IEEE/ACM Transactions on Networking