Doctoral Candidates
| Full Name | Start Time | Research Topic | Published/Accepted Papers |
|---|
| Zhenyu Luo | Fall 2027 | LLM inference optimization | |
|---|
| Yuqiang He | Spring 2027 | Inference engine optimization | |
|---|
| Jinliang Cheng | Fall 2026 | GPU program profiling | |
|---|
| Lai Hu | Fall 2026 | Efficient LLM training | |
|---|
| Yizhen Yu | Fall 2026 | GPU program profiling | |
|---|
| Hangyu Yang | Spring 2026 | Offloading for LLMs | |
|---|
| Guang Huang | Fall 2025 | KV cache optimization | |
|---|
| Guoli Wu | Spring 2025 | LLM inference optimization | |
|---|
| Chengxi Liao | Fall 2024 | Long context LLM inference | ICLR | |
|---|
| Tong Yuan | Fall 2024 | Speculative decoding system | EMNLP |
|---|
| Ruijia Yang | Fall 2024 | Efficient LLM training | DAC |
|---|
| Rui Zhang | Fall 2024 | MoE inference with CPUs and GPUs | IPDPS |
|---|
| Xinhao Huang | Spring 2024 | Model decomposition | NeurIPS, ICML, AAAI, EMNLP |
|---|
| Jihang Li | Fall 2023 | Learning operator acceleration with GPUs | ICDE, CIKM, EMNLP |
|---|
| Minping Chen | Fall 2023 | Efficient fine-tuning for LLMs | ACLx2, AAAI, CIKM, EMNLP |
|---|
| Yuebin Xu | Fall 2023 | Hyper-parameter optimization (HPO) for LLMs | ICLR, EMNLPx2, CIKM |
|---|
| Xuemei Peng | Spring 2023 | Efficient LLM serving | CIKM, ICPP, IPDPS |
|---|
Master's and Undergraduate Students
| Name | Research |
|---|
| Minghao Ma (RBM MPhil student from Fall 2026) | Recursive self improvement |
|---|
| Xiao Ma (RBM MPhil student from Fall 2026) | LLM training |
|---|
| Gengxin Gao (RBM MPhil student from Fall 2025) | RNA sequence analysis |
|---|
| Junshan Tan (Year 4 Undergraduate student at Fall 2025) | AI workload profiling |
|---|
| Rongji Wang (Year 4 Undergraduate student at Fall 2025) | MoE inference optimization |
|---|
| Zhilin Li (Year 4 Undergraduate student at Fall 2025) | Efficient MoE model serving |
|---|
| Zhiyi Chen (Year 4 Undergraduate student at Fall 2025) | HPO for LLMs |
|---|
Alumni
| Name | Academic Period | Employment | Research |
|---|
| Yile Chen | PhD at SCUT, 2021-26 | Postdoc at National Uni. Singapore | Hyper-parameter optimization (HPO) |
|---|
| Hanfeng Liu | PhD at HKUST-GZ, 2022-26 | ML Engineer at Wechat, Tencent | Parallel GBDT training |
|---|
| Haichao Fang | Master at HKUST-GZ, 2024-26 | Startup at Guangzhou | Emotion enhancement for LLMs |
|---|
| Zeyuan Lin | Master at SCUT, 2023-26 | ML Engineer at GZ Futures Exchange | Kernels for CNNs |
|---|
| Youliang Huang | Master at HKUST-GZ, 2023-25 | PhD at Boston University | Efficient fine-tuning for LLMs |
|---|
| Jiyuan Shi | Master at HKUST-GZ, 2023-25 | ML Engineer at WeChat, Tencent | LLM compression |
|---|
| Tong Yuan | Master at HKUST-GZ, 2022-24 | PhD at HKUST-GZ | Structure learning efficiency optimization |
|---|
| Yawen Chen | PhD at SCUT, 2020-24 | Lecturer at Henan University | Kernel optimization and their applications |
|---|
| Jiantong Jiang | PhD at UWA, 2021-24 | Postdoc at Melbourne University | Graphical model efficiency optimization |
|---|
| Peiyu Yang | PhD at UWA, 2021-24 | Postdoc at Melbourne University | Explaining deep neural networks |
|---|