Fangxin (Leon) Liu is an Assistant Professor and Ph.D. supervisor in the School of Computer Science at Shanghai Jiao Tong University (SJTU). I also serve as a Research Fellow at the Shanghai Qi Zhi Institute. My research interests include neural network acceleration (e.g., mixed-precision computing and SW/HW co-design), in-memory computing, and brain-inspired neuromorphic computing.
I received my Ph.D. degree from SJTU in 2023, advised by Prof. Li Jiang. To date, I have published over 60 papers as first or corresponding author, with more than 40 in CCF Tier A venues, including top-tier architecture conferences and journals such as ISCA, MICRO, ASPLOS, HPCA, PPoPP, DAC, IEEE TC, TPDS, and TCAD. My work has been recognized with honors such as the Spark Award from HUAWEI, the Outstanding Doctoral Dissertation Award from the Shanghai Computer Society, the ACM China Shanghai Excellent Doctoral Dissertation Award, and the Best Paper Award at DATE 2022.
40+ CCF Tier A as 1st or Corr. Author
60+ Total Pubs as 1st or Corr. Author
5+ Industrial Adoption Applied at Huawei, Ant, etc.
5+ Major Awards Best Paper/Dissert.
My research has been successfully adopted by leading technology companies, including Huawei, Ant Group, ZTE, and Yizhu Tech., to advance real-world applications such as efficient LLM inference, low-precision deployment, and optimized AI compilation. For instance, my work on mixed-precision computing and SW/HW co-design has enabled up to 40% reductions in computational costs for large-scale AI deployments. I am committed to bridging cutting-edge research with practical industry solutions and welcome opportunities for further collaboration.
🔥 Recruitment
Our team is actively seeking self-motivated PhD, Master, and Undergraduate students interested in Computer Architecture, Efficient AI acceleration, and PIM Design. If you are interested, please email me your CV.
News
Mar. 28, 2026🚀 ISCA 2026: Three papers covering Sparse Matrix Multiplication (Harmonia), MoE Inference Optimization (STEP), and Mobile PIM/CPU Scheduling (COMET) have been accepted to the 53rd International Symposium on Computer Architecture. Congratulations to Jingkui, Ning, Yilong, and all co-authors!
Feb. 24, 2026🚀 Five papers covering Neuromorphic Computing, 3DGS, MoE and PCIe Simulation have been accepted to DAC 2026. Congratulations to Haomin, Chenyang, Zhibai and all co-authors!
Feb. 04, 2026📄 Our joint technical report with Huawei MindSpore team,
HyperOffload, is released. It cuts peak memory by 26% with end-to-end performance lossless. arXiv:
2602.00748 Jan. 24, 2026📄 Our paper "NICE: Deep Neural Network Acceleration via Hardware-Friendly Index Assisted Compression" has been accepted to ACM TACO 2026.
Jan. 21, 2026🏆 Our work “TFLOP” has received the
Special Feature Award at the ASP-DAC University LSI Design Contest 2026.
Nov. 26, 2025📄 Our two papers on MoE memory bottleneck and 3DGS rendering have been accepted to ASPLOS 2026.
Nov. 11, 2025📄 Two papers on graph-based memory and sparse Transformer acceleration accepted to PPoPP 2026.
Nov. 11, 2025📄 Three papers on Modular Multiplication, LLM, and CPU-GPU computing accepted to DATE 2026.
🕒 Click to view all Archived News (2025 - 2022)
Nov. 08, 2025📄 Two papers on 3DGS Acceleration accepted to HPCA 2026.
Nov. 08, 2025📄 Paper "SpecQuant" accepted to AAAI 2026.
Sep. 05, 2025📄 Paper "BLADE" on DRAM-based LLM Acceleration accepted to
ASP-DAC 2026.
Aug. 21, 2025📄 Paper on Flexible Quantization for LLM accepted to EMNLP 2025.
Jul. 06, 2025📄 Adaptive Dynamic Layer-skipping Framework for LLM accepted to ACM MM (Oral) 2025.
Jul. 01, 2025📄 Three papers on PIM-LLM, circuit optimization, and PCIe tracing accepted to ICCAD 2025.
May. 03, 2025📄 Paper on "Collision Detection Accelerator Based on RRAM-TCAMs" accepted to IEEE TCAD 2025.
Apr. 29, 2025📄 Two papers on "PIM+NeRF" and "PIM+Database" accepted by ASPLOS 2026.
Aug. 26, 2024💰 Received grant from NSFC Youth Fund for Adaptive Compression Encoding.
Jul. 06, 2024🏆 Received 2023 ACM Shanghai Doctoral Dissertation Award.
Mar. 18, 2024🏆 Received 2023 Shanghai CCF Outstanding Dissertation Award.
Nov. 18, 2022📄 Paper "SIMSnn" accepted by DATE 2023.
Research
His research bridges the gap between Cutting-edge Architecture and Practical AI Solutions, focusing on:
- LLM & Generative AI Acceleration (Mixed-precision, Quantization, MoE)
- In-Memory Computing (RRAM/DRAM-based PIM/CiM)
- Brain-inspired Computing (Spiking Neural Networks, HDC)
- AI Compilation & HW/SW Co-design
Recent Visits to this Site
