---
title: "Song Han — all works — Elamur Research"
description: "All 34 works of Song Han in the Elamur Research library, the most cited first: our summaries where we have them, else the original."
canonical: "https://research.elamur.ai/free/en/authors/song-han/works/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/song-han/works/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Song Han](https://md.research.elamur.ai/free/en/authors/song-han/) / all works

# Song Han — all works

34 works · [← Song Han](https://md.research.elamur.ai/free/en/authors/song-han/)

1. **[SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and \<0.5MB model size ↗](https://arxiv.org/abs/1602.07360) arXiv (Cornell University) · no summary yet**Forrest Iandola et al.*2016 · 6,402 citations*
2. **[TSM: Temporal Shift Module for Efficient Video Understanding ↗](https://doi.org/10.1109/iccv.2019.00718) IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yet**Ji Lin, Chuang Gan, Song Han*2019 · 2,109 citations*
3. **[AMC: AutoML for Model Compression and Acceleration on Mobile Devices ↗](https://doi.org/10.1007/978-3-030-01234-2_48) arXiv:1802.03494 · no summary yet**Yihui He; Ji Lin; Zhijian Liu; Hanrui Wang; Li-Jia Li;, Song Han*2018 · 1,444 citations*
4. **[EIE: Efficient Inference Engine on Compressed Deep Neural Network ↗](https://arxiv.org/abs/1602.01528) arXiv:1602.01528 · no summary yet**Song Han et al.*2016 · 1,193 citations*
5. **[HAQ: Hardware-Aware Automated Quantization With Mixed Precision ↗](https://doi.org/10.1109/cvpr.2019.00881) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Kuan Wang et al.*2019 · 1,024 citations*
6. **[SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning ↗](https://doi.org/10.1109/hpca51647.2021.00018) arXiv:2012.09852 · no summary yet**Hanrui Wang, Zhekai Zhang, Song Han*2020 · 534 citations*
7. **[ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware ↗](https://arxiv.org/abs/1812.00332) arXiv:1812.00332 · no summary yet**Han Cai, Ligeng Zhu, Song Han*2018 · 479 citations*
8. **[VILA: On Pre-training for Visual Language Models](https://md.research.elamur.ai/free/en/papers/lin-2023-vila-pre-training-visual-language/) [IEEE Computer Society Conference on Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/)**Ji Lin, Hongxu Yin, Wei Ping, et al.*2023 · 381 citations*
9. **[EfficientViT: Lightweight Multi-Scale Attention for High-Resolution Dense Prediction ↗](https://doi.org/10.1109/iccv51070.2023.01587) IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yet**Han Cai et al.*2023 · 363 citations*
10. **[HAT: Hardware-Aware Transformers for Efficient Natural Language Processing](https://md.research.elamur.ai/free/en/papers/wang-2020-hat-hardware-aware-transformers-efficient/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Hanrui Wang, Zhanghao Wu, Zhijian Liu, et al.*2020 · 294 citations*
11. [**LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models arXiv:2309.12307**Yukang Chen, Shengju Qian, Haotian Tang, et al.*2023 · 268 citations*](https://md.research.elamur.ai/free/en/papers/chen-2023-longlora-efficient-fine-tuning-long/)
12. **[Once-for-All: Train One Network and Specialize it for Efficient Deployment ↗](https://arxiv.org/abs/1908.09791) arXiv:1908.09791 · no summary yet**Han Cai et al.*2019 · 252 citations*
13. [**Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference arXiv:2406.10774**Jiaming Tang, Yilong Zhao, Kan Zhu, et al.*2024 · 203 citations*](https://md.research.elamur.ai/free/en/papers/tang-2024-quest-query-aware-sparsity-efficient/)
14. **[QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving ↗](https://arxiv.org/abs/2405.04532) MLSys 2025 · no summary yet**Yujun Lin et al.*2024 · 120 citations*
15. [**DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads arXiv:2410.10819**Guangxuan Xiao, Jiaming Tang, Jingwei Zuo, et al.*2024 · 114 citations*](https://md.research.elamur.ai/free/en/papers/xiao-2024-duoattention-efficient-long-context-llm/)
16. **[NVILA: Efficient Frontier Visual Language Models ↗](https://doi.org/10.1109/cvpr52734.2025.00390) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Zhijian Liu et al.*2025 · 73 citations*
17. [**XAttention: Block Sparse Attention with Antidiagonal Scoring arXiv:2503.16428**Ruyi Xu, Guangxuan Xiao, Haofeng Huang, et al.*2025 · 59 citations*](https://md.research.elamur.ai/free/en/papers/xu-2025-xattention-block-sparse-attention-antidiagonal/)
18. **[Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity ↗](https://arxiv.org/abs/2502.01776) arXiv:2502.01776 · no summary yet**Haocheng Xi et al.*2025 · 56 citations*
19. **[LongVILA: Scaling Long-Context Visual Language Models for Long Videos ↗](https://arxiv.org/abs/2408.10188) arXiv:2408.10188 · no summary yet**Yukang Chen et al.*2024 · 49 citations*
20. **[Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation ↗](https://arxiv.org/abs/2505.18875) arXiv:2505.18875 · no summary yet**Shuo Yang et al.*2025 · 44 citations*
21. **[Radial Attention: O(n n) Sparse Attention with Energy Decay for Long Video Generation ↗](https://arxiv.org/abs/2506.19852) arXiv (Cornell University) · no summary yet**Li, Xingyang et al.*2025 · 23 citations*
22. **[Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models ↗](https://arxiv.org/abs/2211.02048) arXiv:2211.02048 · no summary yet**Muyang Li; Ji Lin; Chenlin Meng; Stefano Ermon; Song Han;, Jun-Yan Zhu*2022 · 19 citations*
23. **[MLSys: The New Frontier of Machine Learning Systems ↗](https://arxiv.org/abs/1904.03257) arXiv (Cornell University) · no summary yet**Alexander Ratner et al.*2019 · 19 citations*
24. **[Twilight: Adaptive Attention Sparsity with Hierarchical Top-p Pruning ↗](https://doi.org/10.52202/085713-3986) neural information processing systems · no summary yet**Chaofan Lin et al.*2025 · 17 citations*
25. **[WorldModelBench: Judging Video Generation Models As World Models ↗](https://doi.org/10.52202/085713-1834) neural information processing systems · no summary yet**Dacheng Li et al.*2025 · 11 citations*
26. **[FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer ↗](https://arxiv.org/abs/2301.08739) arXiv:2301.08739 · no summary yet**Zhijian Liu et al.*2023 · 11 citations*
27. **[Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation ↗](https://arxiv.org/abs/2604.13010) arXiv:2604.13010 · no summary yet**Yecheng Wu, Song Han, Han Cai*2026 · 10 citations*
28. **[Scaling Vision Pre-Training to 4K Resolution ↗](https://doi.org/10.1109/cvpr52734.2025.00900) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Baifeng Shi et al.*2025 · 7 citations*
29. **[Wolf: Dense Video Captioning with a World Summarization Framework ↗](https://arxiv.org/abs/2407.18908) arXiv (Cornell University) · no summary yet**Boyi Li et al.*2024 · 6 citations*
30. **[Radial Attention: O(n n) Sparse Attention with Energy Decay for Long Video Generation ↗](https://doi.org/10.52202/085713-0568) neural information processing systems · no summary yet**Xingyang Li et al.*2025 · 3 citations*
31. **[Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding ↗](https://arxiv.org/abs/2512.01278) arXiv:2512.01278 · no summary yet**Yilong Zhao et al.*2025 · 2 citations*
32. **[Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing ↗](https://arxiv.org/abs/2603.12254) arXiv (Cornell University) · no summary yet**Baifeng Shi et al.*2026 · 1 citation*
33. **[FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution ↗](https://arxiv.org/abs/2608.16157) arXiv:2608.16157 · no summary yet**Shuo Yang et al.*2026 · 1 citation*
34. **[FoundationMotion: Auto-Labeling and Reasoning about Spatial Movement in Videos ↗](https://arxiv.org/abs/2512.10927) arXiv (Cornell University) · no summary yet**Gan, Yulu et al.*2025 · 1 citation*