SH
Song Han
cs.LGcs.CVcs.AIcs.ARcs.CLquant-phstat.MLcs.DCcs.ETcs.NE
On Valency
published · living versionsW_uwxtqkrf·v1 · currentpublished
Learning both Weights and Connections for Efficient Neural Networks
with Jeff Pool, John Tran, William J. Dally
1 version
Preprints & journals
93 papers in the corpus · 2015–2026EGM: Efficient Visual Grounding Language Models2601.13633v3 · Guanqi Zhan, Changye Li, Zhijian Liu et al.2026 · 0 citationsarXiv
Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter2511.16665v3 · Qinghao Hu, Shang Yang, Junxian Guo et al.2025 · 1 citationarXiv
Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation2507.01957v2 · Zhuoyang Zhang, Luke J. Huang, Chengyue Wu et al.2025 · 0 citationsarXiv
Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow2601.14243v2 · Haocheng Xi, Charlie Ruan, Peiyuan Liao et al.2026 · 0 citationsarXiv
Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding2512.01278v1 · Yilong Zhao, Jiaming Tang, Kan Zhu et al.2025 · 0 citationsarXiv
Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning2502.02770v5 · Chaofan Lin, Jiaming Tang, Shuo Yang et al.2025 · 0 citationsarXiv
DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder2509.25182v1 · Junyu Chen, Wenkun He, Yuchao Gu et al.2025 · 0 citationsarXiv
Sailor: Automating Distributed Training over Dynamic, Heterogeneous, and Geo-distributed Clusters2504.17096v2 · Foteini Strati, Zhendong Zhang, George Manos et al.2025 · 9 citationsarXiv
LEGO: Spatial Accelerator Generation and Optimization for Tensor Applications2509.12053v1 · Yujun Lin, Zhekai Zhang, Song Han2025 · 0 citationsarXiv
Micromobility Flow Prediction: A Bike Sharing Station-level Study via Multi-level Spatial-Temporal Attention Neural Network2507.16020v1 · Xi Yang, Jiachen Wang, Song Han et al.2025 · 0 citationsarXiv
DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer2507.04947v1 · Yecheng Wu, Junyu Chen, Zhuoyang Zhang et al.2025 · 1 citationarXiv
Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models2410.10733v8 · Junyu Chen, Han Cai, Junsong Chen et al.2024 · 2 citationsarXiv
QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving2405.04532v3 · Yujun Lin, Haotian Tang, Shang Yang et al.2024 · 6 citationsarXiv
Transitive Array: An Efficient GEMM Accelerator with Result Reuse2504.16339v1 · Cong Guo, Chiyue Wei, Jiaming Tang et al.2025 · 8 citationsarXiv
LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention2502.14866v2 · Shang Yang, Junxian Guo, Haotian Tang et al.2025 · 1 citationarXiv
QuantumNAT: Quantum Noise-Aware Training with Noise Injection, Quantization and Normalization2110.11331v5 · Hanrui Wang, Jiaqi Gu, Yongshan Ding et al.2021 · 8 citationsarXiv
QuEst: Graph Transformer for Quantum Circuit Reliability Estimation2210.16724v2 · Hanrui Wang, Pengyu Liu, Jinglei Cheng et al.2022 · 12 citationsarXiv
Atomique: A Quantum Compiler for Reconfigurable Neutral Atom Arrays2311.15123v3 · Hanrui Wang, Pengyu Liu, Daniel Bochen Tan et al.2023 · 30 citationsarXiv
Qplacer: Frequency-Aware Component Placement for Superconducting Quantum Computers2401.17450v3 · Junyao Zhang, Hanrui Wang, Qi Ding et al.2024 · 0 citationsarXiv
Q-Pilot: Field Programmable Qubit Array Compilation with Flying Ancillas2311.16190v3 · Hanrui Wang, Daniel Bochen Tan, Pengyu Liu et al.2023 · 17 citationsarXiv
BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation2205.13542v3 · Zhijian Liu, Haotian Tang, Alexander Amini et al.2022 · 1,202 citationsarXiv
Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference2406.10774v2 · Jiaming Tang, Yilong Zhao, Kan Zhu et al.2024 · 1 citationarXiv
SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning2012.09852v3 · Hanrui Wang, Zhekai Zhang, Song Han2020 · 411 citationsarXiv
DISQ: Dynamic Iteration Skipping for Variational Quantum Algorithms2308.06634v3 · Junyao Zhang, Hanrui Wang, Gokul Subramanian Ravi et al.2023 · 8 citationsarXiv
DGR: Tackling Drifted and Correlated Noise in Quantum Error Correction via Decoding Graph Re-weighting2311.16214v3 · Hanrui Wang, Pengyu Liu, Yilian Liu et al.2023 · 1 citationarXiv
Efficient Streaming Language Models with Attention Sinks2309.17453v4 · Guangxuan Xiao, Yuandong Tian, Beidi Chen et al.2023 · 36 citationsarXiv
AMC: AutoML for Model Compression and Acceleration on Mobile Devices1802.03494v4 · Yihui He, Ji Lin, Zhijian Liu et al.2018 · 1,486 citationsarXiv
SpArch: Efficient Architecture for Sparse Matrix Multiplication2002.08947v1 · Zhekai Zhang, Hanrui Wang, Song Han et al.2020 · 284 citationsarXiv
GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning2005.00406v1 · Hanrui Wang, Kuan Wang, Jiacheng Yang et al.2020 · 329 citationsarXiv
HAT: Hardware-Aware Transformers for Efficient Natural Language Processing2005.14187v1 · Hanrui Wang, Zhanghao Wu, Zhijian Liu et al.2020 · 238 citationsarXiv
QuantumNAS: Noise-Adaptive Search for Robust Quantum Circuits2107.10845v5 · Hanrui Wang, Yongshan Ding, Jiaqi Gu et al.2021 · 200 citationsarXiv
MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning2110.15352v2 · Ji Lin, Wei-Ming Chen, Han Cai et al.2021 · 50 citationsarXiv
Tiny Machine Learning: Progress and Futures2403.19076v2 · Ji Lin, Ligeng Zhu, Wei-Ming Chen et al.2024 · 182 citationsIEEE Circuits and Systems Magazine, 23(3), pp. 8-34, October 2023
NAPA: Intermediate-level Variational Native-pulse Ansatz for Variational Quantum Algorithms2208.01215v5 · Zhiding Liang, Jinglei Cheng, Hang Ren et al.2022 · 33 citationsarXiv
QuantumSEA: In-Time Sparse Exploration for Noise Adaptive Quantum Circuits2401.05571v1 · Tianlong Chen, Zhenyu Zhang, Hanrui Wang et al.2024 · 5 citationsarXiv
Lightening-Transformer: A Dynamically-operated Optically-interconnected Photonic Transformer Accelerator2305.19533v3 · Hanqing Zhu, Jiaqi Gu, Hanrui Wang et al.2023 · 45 citationsarXiv
RobustState: Boosting Fidelity of Quantum State Preparation via Noise-Aware Variational Training2311.16035v1 · Hanrui Wang, Yilian Liu, Pengyu Liu et al.2023 · 1 citationarXiv
Transformer-QEC: Quantum Error Correction Code Decoding with Transferable Transformers2311.16082v1 · Hanrui Wang, Pengyu Liu, Kevin Shao et al.2023 · 5 citationsarXiv
TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUs2311.12862v1 · Haotian Tang, Shang Yang, Zhijian Liu et al.2023 · 32 citationsarXiv
Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models.37713217 · Li, Muyang, Lin, Ji, Meng, Chenlin et al.2023 · 19 citationsIEEE transactions on pattern analysis and machine intelligence. 2023;45(12):14465-14480
PockEngine: Sparse and Efficient Fine-tuning in a Pocket2310.17752v1 · Ligeng Zhu, Lanxiang Hu, Ji Lin et al.2023 · 14 citations56th IEEE/ACM International Symposium on Microarchitecture (MICRO 2023)
Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models2211.02048v4 · Muyang Li, Ji Lin, Chenlin Meng et al.2022 · 19 citationsarXiv
Retrospective: EIE: Efficient Inference Engine on Sparse and Compressed Neural Network2306.09552v1 · Song Han, Xingyu Liu, Huizi Mao et al.2023 · 1 citationarXiv
SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer2303.17605v1 · Xuanyao Chen, Zhijian Liu, Haotian Tang et al.2023 · 63 citationsarXiv
Hybrid Gate-Pulse Model for Variational Quantum Algorithms2212.00661v1 · Zhiding Liang, Zhixin Song, Jinglei Cheng et al.2022 · 22 citationsarXiv
Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation2205.01271v4 · Yihan Wang, Muyang Li, Han Cai et al.2022 · 133 citationsIEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2022
PVNAS: 3D Neural Architecture Search with Point-Voxel Convolution2204.11797v2 · Zhijian Liu, Haotian Tang, Shengyu Zhao et al.2022 · 52 citationsarXiv
Network Augmentation for Tiny Deep Learning2110.08890v2 · Han Cai, Chuang Gan, Ji Lin et al.2021 · 10 citationsarXiv
Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications2204.11786v1 · Han Cai, Ji Lin, Yujun Lin et al.2022 · 141 citationsACM Transactions on Design Automation of Electronic Systems (TODAES), Volume 27, Issue 3, Article 20, Page 1-50, 2021
TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Devices.33035158 · Lin, Ji, Gan, Chuang, Wang, Kuan et al.2022 · 81 citationsIEEE transactions on pattern analysis and machine intelligence. 2022;44(5):2760-2774
Career total: 205 works. 93 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.