Publications

60+CCF-AOverall Pubs

20+Architecture ISCA / MICRO / HPCA/ ASPLOS

20+EDA & AutomationDAC / ICCAD

3+AwardsBest /Outstanding/ Feature Papers

{=} Equal contribution {*} Corresponding author [Google Scholar Profile]

2026

[ISCA '26]

Harmonia: A Unified Hierarchical Scheduling Framework for Sparse Matrix Multiplication (Top Conf. in Arch)CCF-A

Jingkui Yang=, Fangxin Liu=,*, Xin Ju, Ning Yang, Chenyang Guan, Junjie Wang, Zongwu Wang, Mei Wen, Jian Liu, Li Jiang, Haibing Guan

[Paper][Code][BibTeX]

[ISCA '26]

STEP: Adaptive Spatio-Temporal Expert Prefetching for Low-Latency and Memory-Efficient MoE Inference (Top Conf. in Arch)CCF-A

Fangxin Liu=, Ning Yang=, Zongwu Wang, Chenyang Guan, Haomin Li, Yu Feng, Liqiang Lu, Xiang Li, Siran Yang, Jiamang Wang, Lin Qu, Li Jiang, Haibing Guan

[Paper][Code][BibTeX]

[ISCA '26]

COMET: A Cooperative Scheduling Framework for Concurrent PIM/CPU Execution on Mobile Devices (Top Conf. in Arch)CCF-A

Yilong Zhao=, Fangxin Liu=, Onur Mutlu, Mingyu Gao, Jian Liu, Li Jiang, Haibing Guan

[Paper][Code][BibTeX]

[DAC '26]

GEMM-GS: Accelerating 3D Gaussian Splatting on Tensor Cores with GEMM-Compatible Blending (Top Conf. in EDA)CCF-A

Haomin Li, Bowen Zhu, Fangxin Liu*, Zongwu Wang, Xinran Liang, Li Jiang, Haibing Guan

[Paper][Code][BibTeX]

[DAC '26]

Brain-Like Hyper-Dimensional Graph Learning System with Hardware-Efficient Adaptive Sparsity (Top Conf. in EDA)CCF-A

Haomin Li, Fangxin Liu*, Z. Wang, S. Huang, N. Yang, C. Guan, T. Yang, X. Liang, H. Guan

[Paper][Code][BibTeX]

[DAC '26]

ExQuant: Global Expert Ranking–Guided Mixed-Precision Quantization for Efficient MoE Inference (Top Conf. in EDA)CCF-A

Chenyang Guan, Fangxin Liu=*, Junjie Wang, Ning Yang and Haibing Guan

[Paper][Code][BibTeX]

[DAC '26]

The Phantom of PCIe: Constraining Generative AIs for Practical Peripherals Trace Synthesizing (Top Conf. in EDA)CCF-A

Zhibai Huang, Chen Chen, James Yen, ... Fangxin Liu*, Tao Song, Mingyuan Xia, Zhengwei Qi

[Paper][Code][BibTeX]

[DAC '26]

SkiST: Memory-Efficient Fine-Tuning of Spiking Neural Networks via Spatio-Temporal Adaptation (Top Conf. in EDA)CCF-A

Zhibai Huang, James Yen, Zhixiang Wei, Yun Wang, Fangxin Liu* and Zhengwei Qi

[Paper][Code][BibTeX]

[Tech Report]

HyperOffload: Graph-Driven Hierarchical Memory Management for LLMs on SuperNode Applied at HUAWEI MindSpore

Fangxin Liu=, Qinghua Zhang=, Hanjing Shen=, Zhibo Liang, Li Jiang, Haibing Guan, Xuefeng Jin

[Paper][Code][BibTeX]

[TACO '26]

NICE: Deep Neural Network Acceleration via Hardware-Friendly Index Assisted Compression (Top Jour. in Arch)CCF-A

Ning Yang=, Fangxin Liu=,*, Zongwu Wang, Haomin Li, Li Jiang, and Haibing Guan

[Paper][Code][BibTeX]

[ASPLOS '26]

EARTH: An Efficient MoE Accelerator with Entropy-Aware Speculative Prefetch and Result Reuse Acc: 10.6%

Fangxin Liu=,*, Ning Yang=, Jingkui Yang, Zongwu Wang, Chenyang Guan, Li Jiang, Haibing Guan

[Paper][Code][BibTeX]

[ASPLOS '26]

Nebula: Infinite-Scale 3D Gaussian Splatting in VR via Collaborative Rendering (Top Conf. in Arch)CCF-AAcc: 10.6%

He Zhu, Zheng Liu, Xingyang Li, Anbang Wu, Jieru Zhao, Fangxin Liu, Jingwen Leng, Yu Feng

[Paper][Code][BibTeX]

[PPoPP '26]

BEEMS: Boosting Machine Vision Efficiency via Computation Graph-Based Memory Smoothing (Top Conf. in Sys.)CCF-AAcc: 11.5%

Hanjing Shen, Fangxin Liu=,*, Jian Liu, Li Jiang, and Haibing Guan

[Paper][Code][BibTeX]

[PPoPP '26]

Accelerating Sparse Transformer Inference on GPU (Top Conf. in Sys.)CCF-AAcc: 11.5%

Wenhao Dai, Haodong Deng, Mengfei Rong, Xinyu Yang, Fangxin Liu, Hailong Yang, Qianwen Cao, Qingxiao Sun

[Paper][Code][BibTeX]

[DATE '26]

LaMoS: Enabling Efficient Large Number Modular Multiplication through SRAM-based CiM (Top Conf. in EDA)CCF-BAcc: 25%

Haomin Li, Fangxin Liu*, Chenyang Guan, Zongwu Wang, Li Jiang and Haibing Guan

[Paper][Code][BibTeX]

[AAAI '26]

SpecQuant: Spectral Decomposition and Adaptive Truncation for Ultra-Low-Bit LLMs Quantization (Top Conf. in AI)CCF-AAcc: 17.6%

Zhixiong Zhao, Fangxin Liu=*, Junjie Wang, Chenyang Guan, Zongwu Wang, Li Jiang, Haibing Guan

[Paper][Code][BibTeX]

[HPCA '26]

ORANGE: Exploring Ockham's Razor for Neural Rendering by Accelerating 3DGS on NPUs (Top Conf. in Arch)CCF-AAcc: 19.7%

Haomin Li, Yue Liang, Fangxin Liu=,*, Bowen Zhu, Zongwu Wang, Yu Feng, Li Jiang, and Haibing Guan

[Paper][Code][BibTeX]

[HPCA '26]

Splatonic: Architecture Support for 3D Gaussian Splatting SLAM via Sparse Processing (Top Conf. in Arch)CCF-AAcc: 19.7%

Xiaotong Huang, He Zhu, Tianrui Ma, Fangxin Liu, Zhezhi He, Yiming Gan, Jingwen Leng, Yu Feng, Minyi Guo

[Paper][Code][BibTeX]

[ASPDAC '26]

BLADE: Boosting LLM Decoding's Communication Efficiency in DRAM-based PIM (Top Conf. in EDA)CCF-AAcc: 29%

Yilong Zhao, Fangxin Liu*, Zongwu Wang, Mingjian Li, Mingxing Zhang, Chixiao Chen, Li Jiang

[Paper][Code][BibTeX]

[ASPLOS '26]

ASDR: Exploiting Adaptive Sampling and Data Reuse for CIM-based Instant Neural Rendering (Top Conf. in Arch)CCF-AAcc: 23%

Fangxin Liu=*, Haomin Li=, Bowen Zhu, Zongwu Wang, Zhuoran Song, Haibing Guan, and Li Jiang

[Paper][Code][BibTeX]

[ASPLOS '26]

PUSHtap: PIM-based In-Memory HTAP with Unified Data Storage Format (Top Conf. in Arch)CCF-AAcc: 23%

Yilong Zhao, Mingyu Gao, Huanchen Zhang, Fangxin Liu*, Gongye Chen, He Xian, Haibing Guan, and Li Jiang

[Paper][Code][BibTeX]

2025

[TACO '25]

Rethinking Variable-Length Encoding: Bit Sparsity for Parallel Decoding in LLM Accelerators (Top Jour. in Arch)CCF-A

Ning Yang, Fangxin Liu*, Junjie Wang, Chenyang Guan, Zongwu Wang, Junping Zhao, Li Jiang, Haibing Guan

[Paper][Code][BibTeX]

[TACO '25]

MIX-PC: Enabling Efficient DNN Inference with Mixed Numeric Precision Compilation Optimization (Top Jour. in Arch)CCF-A

Shiyuan Huang, Fangxin Liu=,*, Zongwu Wang, Ning Yang, Haomin Li, Haibing Guan, and Li Jiang

[Paper][Code][BibTeX]

[EMNLP '25]

FlexQuant: A Flexible and Efficient Dynamic Precision Switching Framework for LLM Quantization (Top Conf. in NLP)CCF-BApplied at Ant Group

Fangxin Liu=, Wongwu Wang, Jinhong Xia, Junping Zhao*, Shouren Zhao, Li Jiang*, Haibing Guan

[Paper][Code][BibTeX]

[ACM MM '25]

ASTER: Adaptive Dynamic Layer-Skipping for Efficient Transformer Inference via MDP (Top Conf. in Multimedia/AI)CCF-A🏆 Outstanding Paper

Fangxin Liu=*, Junjie Wang=, Ning Yang, Zongwu Wang, Junping Zhao, Li Jiang, and Haibing Guan

[Paper][Code][BibTeX]

[ICCAD '25]

QUARK: Quantization-Enabled Circuit Sharing for Transformer Acceleration via Pattern Exploiting (Top Conf. in EDA)CCF-BAcc: 24%

Zhixiong Zhao=, Haomin Li=, Fangxin Liu*, Yuncheng Lu, Zongwu Wang, Tao Yang, Haibing Guan, and Li Jiang

[Paper][Code][BibTeX]

[ICCAD '25]

PLAIN: Leveraging High Internal Bandwidth in PIM for LLM Inference via Mixed-Precision (Top Conf. in EDA)CCF-BAcc: 24%

Yiwei Hu, Fangxin Liu=*, Zongwu Wang, Yilong Zhao, Tao Yang, Haibing Guan, and Li Jiang

[Paper][Code][BibTeX]

[ICCAD '25]

DevTrace: Efficient and Fine-grained PCIe Transaction Tracing for Edge Intelligence Workloads (Top Conf. in EDA)CCF-BAcc: 24%

Zhibai Huang, Kailiang Xu, Zhixiang Wei, Yinghao Deng, Chen Chen, James Yen, Fangxin Liu*, MingYuan Xia, Zhengwei Qi

[Paper][Code][BibTeX]

[TCAD '25]

A Sub-10 μs In-Memory-Search Collision Detection Accelerator Based on RRAM-TCAMs (Top Jour. in EDA)CCF-A

Jiahao Sun, Yijian Zhang, Fangxin Liu*, Li Jiang, and Rui Yang

[Paper][Code][BibTeX]

[TACO '25]

Attack and Defense: Enhancing Robustness of Binary Hyper-Dimensional Computing (Top Jour. in Arch)CCF-A

Haomin Li, Fangxin Liu*, Zongwu Wang, Ning Yang, Shiyuan Huang, Xiaoyao Liang, and Li Jiang

[Paper][Code][BibTeX]

[ISCA '25]

FATE: Boosting HDC Intelligence Performance with Flexible Numerical Data Type (Top Conf. in Arch)CCF-AAcc: 21%

Haomin Li=, Fangxin Liu=*, Yichi Chen, Zongwu Wang, Shiyuan Huang, Ning Yang, Dongxu Lyu, Li Jiang

[Paper][Code][BibTeX]

[ISCA '25]

Qtenon: Towards Low-Latency Architecture Integration for Accelerating Hybrid Quantum-Classical Computing (Top Conf. in Arch)CCF-AAcc: 21%

Chenning Tao, Liqiang Lu, Size Zheng, Li-Wen Chang, Minghua Shen, Hanyu Zhang, Fangxin Liu, Kaiwen Zhou, Jianwei Yin

[Paper][Code][BibTeX]

[DAC '25]

ALLMod: Exploring Area-Efficiency of LUT-based Large Number Modular Reduction via Hybrid Workloads (Top Conf. in EDA)CCF-AAcc: 23%

Fangxin Liu=, Haomin Li=, Zongwu Wang, Bo Zhang, Mingzhe Zhang, Shoumeng Yan, Li Jiang, Haibing Guan

[Paper][Code][BibTeX]

[DAC '25]

MILLION: MasterIng Long-Context LLM Inference Via Outlier-Immunized KV Product Quantization (Top Conf. in EDA)CCF-AApplied at HUAWEI

Zongwu Wang=, Peng Xu=, Fangxin Liu*, Yiwei Hu, Qingxiao Sun, Xuan Wang, Li Jiang, Haibing Guan

[Paper][Code][BibTeX]

[DAC '25]

BLOOM: Bit-Slice Framework for DNN Acceleration with Mixed-Precision (Top Conf. in EDA)CCF-AApplied at ZTE

Fangxin Liu=*, Ning Yang=, Zongwu Wang, Xuanpeng Zhu, Haidong Yao, Xiankui Xiong, Li Jiang, Haibing Guan

[Paper][Code][BibTeX]

[DAC '25]

PISA: Efficient Precision-Slice Framework for LLMs with Adaptive Numerical Type (Top Conf. in EDA)CCF-AAcc: 23%

Ning Yang, Zongwu Wang, Qingxiao Sun, Liqiang Lu, and Fangxin Liu*

[Paper][Code][BibTeX]

[DATE '25]

HyperDyn: Dynamic Dimensional Masking for Efficient Hyper-Dimensional Computing (Top Conf. in EDA)CCF-BAcc: 21%

Fangxin Liu=, Haomin Li=, Zongwu Wang, Dongxu Lyu, and Li Jiang

[Paper][Code][BibTeX]

[DATE '25]

HyperNeO: Efficient and Accurate Hyper-Dimensional Regression via Neural Optimization (Top Conf. in EDA)CCF-BAcc: 21%

Fangxin Liu=, Haomin Li=, Zewen Sun, Zongwu Wang, and Li Jiang

[Paper][Code][BibTeX]

[DATE '25]

TAIL: Temporal Asynchronous Execution for Efficient SNNs with Inter-Layer Parallelism (Top Conf. in EDA)CCF-BAcc: 21%

Haomin Li=, Fangxin Liu=, Z. Wang, D. Lyu, S. Huang, N. Yang, Q. Sun, Z. Song, Li Jiang

[Paper][Code][BibTeX]

[DATE '25]

OPS: Outlier-aware Precision-Slice Framework for LLM Acceleration (Top Conf. in EDA)CCF-BAcc: 21%

Fangxin Liu=, Ning Yang=, Zongwu Wang, Xuanpeng Zhu, Haidong Yao, Xiankui Xiong, Qi Sun, Li Jiang

[Paper][Code][BibTeX]

[DATE '25]

EVASION: Efficient KV Cache Compression via Product Quantization (Top Conf. in EDA)CCF-BAcc: 21%

Zongwu Wang, Fangxin Liu, Peng Xu, Qingxiao Sun, Junping Zhao and Li Jiang

[Paper][Code][BibTeX]

[HPCA '25]

CROSS: Compiler-Driven Optimization of Sparse DNNs Using Sparse/Dense Computation Kernels (Top Conf. in Arch)CCF-AAcc: 21%

Fangxin Liu=, Shiyuan Huang=, Ning Yang, Zongwu Wang, Haomin Li, and Li Jiang

[Paper][Code][BibTeX]

[HPCA '25]

GSArch: Breaking Memory Barriers in 3D Gaussian Splatting Training via Architectural Support (Top Conf. in Arch)CCF-AAcc: 21%

Houshu He, Gang Li, Fangxin Liu, Li Jiang, Xiaoyang Liang, and Zhuoran Song

[Paper][Code][BibTeX]

[ASPDAC '25]

Exploiting Differential-Based Data Encoding for Enhanced Query Efficiency Acc: 28%

Fangxin Liu=, Zongwu Wang=, Peng Xu, Shiyuan Huang and Li Jiang

[Paper][Code][BibTeX]

[ASPDAC '25]

NeuronQuant: Accurate and Efficient Post-Training Quantization for Spiking Neural Networks Acc: 28%

Haomin Li=, Fangxin Liu=, Zewen Sun, Zongwu Wang, Shiyuan Huang, Ning Yang, and Li Jiang

[Paper][Code][BibTeX]

2024

[TCAS-AI '24]

SearchQ: Search-based Fine-Grained Quantization for Data-Free Model Compression Applied at HUAWEI

Ning Yang=, Fangxin Liu=, Zongwu Wang, Junping Zhao, Li Jiang

[Paper][Code][BibTeX]

[TODAES '24]

STCO: Enhancing Training Efficiency via Structured Sparse Tensor Compilation Optimization Applied at Yizhu Tech.

Shiyuan Huang=, Fangxin Liu=, Tian Li, Zongwu Wang, Ning Yang, Haomin Li and Li Jiang

[Paper][Code][BibTeX]

[TCAD '24]

SpMMPlu-Pro: An Enhanced Compiler Plug-In for Efficient SpMM and Sparsity Propagation (Top Jour. in EDA)CCF-A

Shiyuan Huang, Fangxin Liu*, Tao Yang, Zongwu Wang Ning Yang, and Li Jiang

[Paper][Code][BibTeX]

[ICCD '24]

T-BUS: Taming Bipartite Unstructured Sparsity for Energy-Efficient DNN Acceleration Acc: 25%

Fangxin Liu=, Ning Yang=, Zongwu Wang, Zhiyan Song, Tao Yang, and Li Jiang

[Paper][Code][BibTeX]

[ICCD '24]

HOLES: Boosting LLMs Efficiency with Hardware-friendly Lossless Encoding Acc: 25%

Fangxin Liu=, Ning Yang=, Zhiyan Song, Zongwu Wang and Li Jiang

[Paper][Code][BibTeX]

[ICCD '24]

PS4: A Low Power SNN Accelerator with Spike Speculative Scheme Acc: 25%

Zongwu Wang=, Fangxin Liu=, and Li Jiang

[Paper][Code][BibTeX]

[ICCD '24]

Ninja: A Hardware Assisted System for Accelerating Nested Address Translation Acc: 25%

Longyu Zhao, Zongwu Wang, Fangxin Liu*, and Li Jiang

[Paper][Code][BibTeX]

[MICRO '24]

COMPASS: SRAM-Based Computing-in-Memory SNN Accelerator with Adaptive Spike Speculation (Top Conf. in Arch)CCF-AAcc: 22%

Zongwu Wang, Fangxin Liu*, Ning Yang, Shiyuan Huang, Haomin Li, and Li Jiang

[Paper][Code][BibTeX]

[MICRO '24]

SRender: Boosting Neural Radiance Field Efficiency via Sensitivity-Aware Dynamic Precision Rendering (Top Conf. in Arch)CCF-AAcc: 22%

Zhuoran Song, Houshu He, Fangxin Liu*, Yifan Hao, Xinkai Song, Li Jiang and Xiaoyao Liang

[Paper][Code][BibTeX]

[TPDS '24]

Exploiting Temporal-Unrolled Parallelism for Energy-Efficient SNN Acceleration (Top Jour. in Arch)CCF-A

Fangxin Liu, Z. Wang, W. Zhao, N. Yang, Y. Chen, S. Huang, H. Li, T. Yang, S. Pei, X. Liang, Li Jiang

[Paper][Code][BibTeX]

[ISLPED '24]

LowPASS: A Low power PIM-based accelerator with Speculative Scheme for SNNs Acc: 21%

Zongwu Wang, Fangxin Liu*, Longyu Zhao, Shiyuan Huang and Li Jiang

[Paper][Code][BibTeX]

[ISCA '24]

UM-PIM: DRAM-based PIM with Uniform & Shared Memory Space (Top Conf. in Arch)CCF-AAcc: 18%

Yilong Zhao, Mingyu Gao, Fangxin Liu*, Yiwei Hu, Zongwu Wang, Han Lin, Ji Li, He Xian, Naifeng Jing, Li Jiang

[Paper][Code][BibTeX]

[DAC '24]

INSPIRE: Accelerating Deep Neural Networks via Hardware-friendly Index-Pair Encoding (Top Conf. in EDA)CCF-AAcc: 23%

Fangxin Liu=, Ning Yang=, Haomin Li, Zongwu Wang, Zhuoran Song, Songwen Pei, Li Jiang

[Paper][Code][BibTeX]

[DAC '24]

EOS: An Energy-Oriented Attack Framework for Spiking Neural Networks (Top Conf. in EDA)CCF-AAcc: 23%

Fangxin Liu=, Ning Yang=, Haomin Li, Zongwu Wang, Zhuoran Song, Songwen Pei, Li Jiang

[Paper][Code][BibTeX]

[DATE '24]

RTSA: An RRAM-TCAM based In-Memory-Search Accelerator for Sub-100 μs Collision Detection (Top Conf. in EDA)CCF-BAcc: 24%

Jiahao Sun, Fangxin Liu=, Yijian Zhang, Li Jiang and Rui Yang

[Paper][Code][BibTeX]

[ASPLOS '24]

CMC: Video Transformer Acceleration via CODEC Assisted Matrix Condensing (Top Conf. in Arch)CCF-AAcc: 24%

Zhuoran Song, Chunyu Qi, Fangxin Liu=, Naifeng Jing, Xiaoyao Liang

[Paper][Code][BibTeX]

[HPCA '24]

SPARK: Scalable and Precision-Aware Acceleration of Neural Networks via Efficient Encoding (Top Conf. in Arch)CCF-AAcc: 18%

Fangxin Liu=, Ning Yang=, Haomin Li, Zongwu Wang, Zhuoran Song, Songwen Pei, Li Jiang

[Paper][Code][BibTeX]

[ASPDAC '24]

PAAP-HD: PIM-Assisted Approximation for Efficient Hyper-Dimensional Computing (Top Conf. in EDA)Acc: 29%

Fangxin Liu=, Haomin Li=, Ning Yang, Yichi Chen, Zongwu Wang, Tao Yang, Li Jiang

[Paper][Code][BibTeX]

[ASPDAC '24]

TEAS: Exploiting Spiking Activity for Temporal-wise Adaptive Spiking Neural Networks (Top Conf. in EDA)Acc: 29%

Fangxin Liu=, Haomin Li=, Ning Yang, Zongwu Wang, Tao Yang, Li Jiang

[Paper][Code][BibTeX]

[ASPDAC '24]

TSTC: Enabling Efficient Training via Structured Sparse Tensor Compilation (Top Conf. in EDA)Acc: 29%

Shiyuan Huang=, Fangxin Liu=, Tian Li, Zongwu Wang, Haomin Li, Li Jiang

[Paper][Code][BibTeX]

[ASPDAC '24]

HyperFeel: An Efficient Federated Learning Framework Using Hyperdimensional Computing (Top Conf. in EDA)Acc: 29%

Haomin Li=, Fangxin Liu=, Yichi Chen, Li Jiang

[Paper][Code][BibTeX]

[DAC '24]

HyperAttack: An Efficient Attack Framework for HyperDimensional Computing (Top Conf. in EDA)CCF-AAcc: 23%

Fangxin Liu=, Haomin Li=, Zongwu Wang, Yongbiao Chen, Li Jiang

[Paper][Code][BibTeX]

2023

[IEEE TC '23]

ERA-BS: Efficiency of ReRAM-based PIM Accelerator with Fine-Grained Bit-Level Sparsity (Top Jour. in Arch)CCF-A

Fangxin Liu, Wenbo Zhao, Zongwu Wang, Yongbiao Chen, Xiaoyao Liang, Li Jiang

[Paper][Code][BibTeX]

[ICCD '23]

PSQ: An Automatic Search Framework for Data-Free Quantization on PIM-based Architecture Acc: 28%

Fangxin Liu=, Ning Yang=, Li Jiang

[Paper][Code][BibTeX]

[ICCAD '23]

HyperNode: An Efficient Node Classification Framework Using HyperDimensional Computing (Top Conf. in EDA)Acc: 23%

Haomin Li=, Fangxin Liu=, Yichi Chen, Li Jiang

[Paper][Code][BibTeX]

2022

[SIGIR '22]

L3E-HD: A Framework Enabling Efficient Ensemble in High-Dimensional Space for Language Tasks (Top Conf. in IR)Acc: 24%

Fangxin Liu, Haomin Li, Xiaokang Yang, Li Jiang

[Paper][Code][BibTeX]

[TCAD '22]

IVQ: In-Memory Acceleration of DNN Inference Exploiting Varied Quantization CCF-A(Top Jour. in EDA)

Fangxin Liu=, Wenbo Zhao, Zongwu Wang, Yilong Zhao, Tao Yang, Yiran Chen, Li Jiang

[Paper][Code][BibTeX]

[DAC '22]

EBSP: Evolving Bit Sparsity Patterns for Hardware Friendly Inference of Quantized Deep Neural Networks (Top Conf. in EDA)Acc: 24.7%

Fangxin Liu, Wenbo Zhao, Zongwu Wang, Yongbiao Chen, Zhezhi He, Naifeng Jing, Xiaoyao Liang, Li Jiang

[Paper][Code][BibTeX]

[DAC '22]

PIM-DH: ReRAM based Processing in Memory Architecture for Deep Hashing Acceleration Acc: 24.7%

Fangxin Liu=, Wenbo Zhao, Yongbiao Chen, Zongwu Wang, Zhezhi He, Rui Yang, Qidong Tang, Tao Yang, Cheng Zhuo

[Paper][Code][BibTeX]

[DAC '22]

SATO: Spiking Neural Network Acceleration via Temporal Oriented Dataflow and Architecture Acc: 24.7%

Fangxin Liu, Wenbo Zhao, Zongwu Wang, Yongbiao Chen, Tao Yang, Zhezhi He, Xiaokang Yang, Li Jiang

[Paper][Code][BibTeX]

[DATE '22]

Self-Terminated Write of MLC ReRAM for Efficient Neuromorphic Computing 🏆 Best Paper Award(Top Conf. in EDA)

Zongwu Wang, Fangxin Liu, et al.

[Paper][Code][BibTeX]

[AAAI '22]

SpikeConverter: An Efficient Conversion Framework Zipping the Gap between ANNs and SNNs 🏆 Oral (Top 15%)(Top Conf. in AI)

Fangxin Liu, Wenbo Zhao*, Yongbiao Chen, Zongwu Wang, Li Jiang

[Paper][Code][BibTeX]

[ICASSP '22]

Dynsnn: A dynamic approach to reduce redundancy in spiking neural networks (Top Conf. in Signal Processing)CCF-B

Fangxin Liu=, Wenbo Zhao, Yongbiao Chen, Zongwu Wang, Fei Dai

[Paper][Code][BibTeX]

[DATE '22]

DTQAtten: Leveraging Dynamic Token-based Quantization for Efficient Attention Best Paper Nomination

Tao Yang, Fangxin Liu, et al.

[Paper][Code][BibTeX]

[ASPDAC '22]

HAWIS: Hardware-Aware Automated Width Search for Accurate Robust BNN on ReRAM (Top Conf. in EDA)

Qidong Tang, Fangxin Liu, et al.

[Paper][Code][BibTeX]

[DAC '22]

PIMGCN: A ReRAM-based PIM Design for Graph Convolutional Network Acceleration (Top Conf. in EDA)

Tao Yang, Fangxin Liu, et al.

[Paper][Code][BibTeX]

[ICMR '22]

TransHash: Transformer-based Hamming Hashing for Efficient Image Retrieval

Yongbiao Chen, Fangxin Liu, et al.

[Paper][Code][BibTeX]

2021

[Frontiers '21]

SSTDP: Supervised Spike Timing Dependent Plasticity for Efficient SNN Training (SCI Tier 2, Impact Factor: 4.7)

Fangxin Liu=, Wenbo Zhao=, Yongbiao Chen, Zongwu Wang, Tao Yang, Li Jiang

[Paper][Code][BibTeX]

[ICCD '21]

SME: ReRAM-based Sparse-Multiplication-Engine to Squeeze-Out Bit Sparsity of NN Acc: 24.4%

Fangxin Liu, Wenbo Zhao, Zhezhi He, Zongwu Wang, Yilong Zhao, Tao Yang, Jingnai Feng, Xiaoyao Liang, Li Jiang

[Paper][Code][BibTeX]

[ICCV '21]

Improving NN Efficiency via Post-training Quantization with Adaptive Floating-Point Acc: 25.9%(Top Conf. in Vision)

Fangxin Liu=, Wenbo Zhao, Zhezhi He, Yanzhi Wang, Zongwu Wang, Changzhi Dai, Xiaoyao Liang, Li Jiang

[Paper][Code][BibTeX]

[ICCAD '21]

Bit-Transformer: Transforming Bit-level Sparsity into Higher Preformance in ReRAM-based Accelerator (Top Conf. in EDA)Acc: 23.5%

Fangxin Liu, Wenbo Zhao, Zhezhi He, Zongwu Wang, Yilong Zhao, Yongbiao Chen, Li Jiang

[Paper][Code][BibTeX]

[GLSVLSI '21]

IM3A: Boosting Deep Neural Network Efficiency via In-Memory Addressing-Assisted Acceleration Acc: 24%

Fangxin Liu=, Wenbo Zhao, Zongwu Wang, Tao Yang, Li Jiang

[Paper][Code][BibTeX]

--------