Zi-Han Liu

Most-cited papers

ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization
Cong Guo, Chen Zhang, Jingwen Leng, Zi-Han Liu +4 more
2022Micro141 citations Open access
Semantic Scholar
VELTAIR: towards high-performance multi-tenant deep learning services via adaptive compilation and scheduling
Zi-Han Liu, Jingwen Leng, Zhihui Zhang, Quan Chen +2 more
2022International Conference on Architectural Support for Programming Languages and Operating Systems64 citations Open access
Semantic Scholar
GMLake: Efficient and Transparent GPU Memory Defragmentation for Large-scale DNN Training with Virtual Memory Stitching
Cong Guo, Rui Zhang, Jiale Xu, Jingwen Leng +7 more
2024International Conference on Architectural Support for Programming Languages and Operating Systems46 citations Open access
Semantic Scholar
JUNO: Optimizing High-Dimensional Approximate Nearest Neighbour Search with Sparsity-Aware Algorithm and Ray-Tracing Core Mapping
Zi-Han Liu, Wentao Ni, Jingwen Leng, Yu Feng +5 more
2023International Conference on Architectural Support for Programming Languages and Operating Systems41 citations Open access
Semantic Scholar
Cicero: Addressing Algorithmic and Architectural Bottlenecks in Neural Rendering by Radiance Warping and Memory Optimizations
Yu Feng, Zi-Han Liu, Jingwen Leng, Min-Yi Guo +1 more
2024International Symposium on Computer Architecture34 citations Open access
Semantic Scholar
M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type
Weiming Hu, Haoyang Zhang, Cong Guo, Yu Feng +6 more
2025International Symposium on High-Performance Computer Architecture33 citations Open access
Semantic Scholar
VQ-LLM: High-performance Code Generation for Vector Quantization Augmented LLM Inference
Zi-Han Liu, Xin-Hao Luo, Junxian Guo, Wentao Ni +10 more
2025International Symposium on High-Performance Computer Architecture26 citations Open access
Semantic Scholar
SeeLe: A Unified Acceleration Framework for Real-Time Gaussian Splatting
Xiaotong Huang, He Zhu, Zi-Han Liu, Wei-Kai Lin +5 more
2025arXiv.org25 citations
Semantic Scholar
vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving
Jiale Xu, Rui Zhang, Cong Guo, Weiming Hu +10 more
2024arXiv.org25 citations
Semantic Scholar
Lumina: Real-Time Neural Rendering by Exploiting Computational Redundancy
Yu Feng, Wei-Kai Lin, Yuge Cheng, Zi-Han Liu +5 more
2025International Symposium on Computer Architecture15 citations Open access
Semantic Scholar
SPLATONIC: Architectural Support for 3D Gaussian Splatting SLAM via Sparse Processing
Xiaotong Huang, He Zhu, Tianrui Ma, Yuxiang Xiong +7 more
2025International Symposium on High-Performance Computer Architecture13 citations
Semantic Scholar
ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive
Xin-Hao Luo, Zi-Han Liu, Yang-Jie Zhou, Shihan Fang +7 more
2025Neural Information Processing Systems10 citations
Semantic Scholar
Astraea: A Token-wise Acceleration Framework for Video Diffusion Transformers
Haosong Liu, Yuge Cheng, Wen-Xuan Miao, Zi-Han Liu +7 more
202510 citations
Semantic Scholar
Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy
Yu Feng, Wei-Kai Lin, Yuge Cheng, Zi-Han Liu +5 more
2025arXiv.org9 citations
Semantic Scholar
eLLM: Elastic Memory Management Framework for Efficient LLM Serving
Jiale Xu, Rui Zhang, Yi Xiong, Cong Guo +10 more
2025arXiv.org8 citations
Semantic Scholar
A Sample-Free Compilation Framework for Efficient Dynamic Tensor Computation
Yang-Jie Zhou, Honglin Zhu, Qian Qiu, Wei-Hao Cui +12 more
2025International Conference on Software Composition8 citations Open access
Semantic Scholar
DLFusion: An Auto-Tuning Compiler for Layer Fusion on Deep Neural Network Accelerator
Zi-Han Liu, Jingwen Leng, Quan Chen, Chao Li +3 more
20202020 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom)8 citations Open access
Semantic Scholar
AdaptGear: Accelerating GNN Training via Adaptive Subgraph-Level Kernels on GPUs
Yang-Jie Zhou, Yao-Xu Song, Jingwen Leng, Zi-Han Liu +6 more
2023ACM International Conference on Computing Frontiers7 citations Open access
Semantic Scholar
StreamGrid: Streaming Point Cloud Analytics via Compulsory Splitting and Deterministic Termination
Yu Feng, Zheng Liu, Wei-Kai Lin, Zi-Han Liu +5 more
2025International Conference on Architectural Support for Programming Languages and Operating Systems6 citations
Semantic Scholar
Voyager: Input-Adaptive Algebraic Transformations for High-Performance Graph Neural Networks
Yang-Jie Zhou, Wen Shen, Jingwen Leng, Shuwen Lu +12 more
2025International Conference on Architectural Support for Programming Languages and Operating Systems5 citations Open access
Semantic Scholar
FlashFuser: Expanding the Scale of Kernel Fusion for Compute-Intensive Operators via Inter-Core Connection
Ziyu Huang, Yang-Jie Zhou, Zi-Han Liu, Xin-Hao Luo +7 more
2025International Symposium on High-Performance Computer Architecture5 citations Open access
Semantic Scholar
SLTarch: Towards Scalable Point-Based Neural Rendering by Taming Workload Imbalance and Memory Irregularity
Xingyang Li, Jie Jiang, Yu Feng, Yiming Gan +4 more
20252025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)5 citations
Semantic Scholar
CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels
Xing-Chen Ma, Yang-Jie Zhou, Wu Sun, Zi-Han Liu +5 more
2026Annual Meeting of the Association for Computational Linguistics4 citations Open access
Semantic Scholar
Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM Decoding
Yue Guan, Changming Yu, Shihan Fang, Weiming Hu +7 more
2025Neural Information Processing Systems4 citations
Semantic Scholar
Vortex: Efficient Sample-Free Dynamic Tensor Program Optimization via Hardware-aware Strategy Space Hierarchization
Yang-Jie Zhou, Honglin Zhu, Qian Qiu, Wei-Hao Cui +8 more
2024arXiv.org3 citations
Semantic Scholar
GPU-Tile-Sim: A Tile-Centric GPU Simulation Framework for LLM Hardware-Software Co-Design
Yitong Ding, Jiawei Huang, Renyang Guan, Yang-Jie Zhou +6 more
2026arXiv.org2 citations
Semantic Scholar
JUNO++: Optimizing ANNS and Enabling Efficient Sparse Attention in LLM via Ray Tracing Core
Zi-Han Liu, Wentao Ni, Jingwen Leng, Yu Feng +7 more
2025ACM Transactions on Architecture and Code Optimization (TACO)2 citations Open access
Semantic Scholar
Survey and design of paleozoic: a high-performance compiler tool chain for deep learning inference accelerator
Zi-Han Liu, Jingwen Leng, Guandong Lu, Chenhui Wang +2 more
2020CCF Transactions on High Performance Computing2 citations
Semantic Scholar
Deltoris: Enabling Real-time VLA Inference in Embodied AI via Bit-level Sparsity and Speculative Inference
Zheng Liu, Zeyu Guo, Zi-Han Liu, An-Bang Wu +8 more
20261 citations
Semantic Scholar
Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Transformers by Exploiting Latent Space Correlations
Wen-Xuan Miao, Haosong Liu, Weiming Hu, Zi-Han Liu +8 more
2026arXiv.org1 citations
Semantic Scholar
DFlow: Efficient Dataflow-based Invocation Workflow Execution for Function-as-a-Service
Xiaoxiang Shi, C. Li, Zi-Jun Li, Zi-Han Liu +4 more
2023arXiv.org1 citations Open access
Semantic Scholar
AlphaCu: A Transformation-Driven Synthesis Framework for LLM-Based GPU Kernel Generation
Yang-Jie Zhou, Xing-Chen Ma, Zi-Han Liu, Qing Wang +8 more
2026Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering0 citations Open access
Semantic Scholar
A Thread-Register Decoupled GPU Execution Model for Efficient Tensor Computation
Zi-Han Liu, Jingwen Leng, Yang-Jie Zhou, Yitong Ding +11 more
20260 citations
Semantic Scholar
Elastic GPU architecture simulation framework with fined-grained tile dataflow
Zi-Han Liu, Yitong Ding, Renyang Guan, Jiawei Huang +4 more
2026Scientia Sinica Informationis0 citations
Semantic Scholar
Atlas: Algorithm-Hardware Co-Design for On-Device City-Scale 3D Gaussian Splatting in VR
He Zhu, Zheng Liu, Xingyang Li, An-Bang Wu +7 more
20260 citations
Semantic Scholar