Architecture
- Efficient Domain-Specific Accelerators (DSA) for LLM/VLA
- Near-Memory / Processing-in-Memory (PIM) Computing
Biography
I am an Assistant Professor in the Microelectronics Thrust at The Hong Kong University of Science and Technology (Guangzhou). Before joining HKUST(GZ), I was a Principal Engineer at Hisilicon, working on next-generation DPUs. I received my Ph.D. in computer science from the National University of Singapore (NUS) in 2022, where I was supervised by Prof. Bingsheng He and collaborated closely with Prof. Weng-Fai Wong and Prof. Deming Chen.
I lead the Custom Computing Lab (CLab) at HKUST(GZ). Our group develops sustainable computing solutions for AI and big data through customized hardware architectures and specialized system designs.
Research Areas
System
- Efficient system design for LLMs/VLAs
- Heterogeneous computing with FPGA, GPU, and NPUs
Algorithm
- Hardware-aware algorithms for efficient AI computing
- Algorithm-system-architecture co-design
Openings
I am actively recruiting self-motivated candidates for the following positions:
- PhD Students
- MPhil Students
- Research Assistants
Applicants with backgrounds in computer engineering, computer science, electronic engineering, or related fields are welcome.
We also have open positions focusing on Vision-Language-Action (VLA) models and Embodied AI.
Recent News
All news →- Paper Our papers “TensorBridge: Bridging Microscaled FP4 Weights to FP8 Tensor Cores for LLM Serving” and “InfiniLoRA: Disaggregated Multi-LoRA Serving for Large Language Models” have been Accepted to ATC 2026.
- Paper Five papers, “Sparse by Command”, “Ultra-DSP”, “RidgeBridge”, “SCOPE”, and “MFNNS”, have been accepted to MICRO 2026. Congratulations to Afzal, Chenyu, Chenxi, Hongshi, and Rui for the great work!
- Paper Our paper “SAFS: Slack-Aware Flow Scheduling transport for pipelined AI workload” has been Accepted to ICNP 2026.
- Paper Our paper “MixFP4: Enhancing NVFP4 with Adaptive FP4/INT4 Block Representations” has been accepted to ICML 2026. Congratulations to Jiaxiang!
- Paper Our paper “UniCore: A Bit-Width Scalable GEMM Unit for Unified LLM Inference” has been accepted to ISCA 2026. Congratulations to Yonghao and Jiaxiang for the great work!
Awards
- First Prize, Graph Computing System Design Challenge CCF SYS · 2025
- AMD HACC Outstanding Researcher Award AMD · 2023
- NUS Research Achievement Award National University of Singapore · 2022