| Deep Leakage from Gradients L Zhu, Z Liu, S Han Neural Information Processing Systems (NeurIPS), 2019, 2019 | 3582 | 2019 |
| Proxylessnas: Direct neural architecture search on target task and hardware H Cai, L Zhu, S Han International Conference on Learning Representations (ICLR), 2019, 2018 | 2624 | 2018 |
| Tinytl: Reduce memory, not parameters for efficient on-device learning H Cai, C Gan, L Zhu, S Han Advances in Neural Information Processing Systems 33, 11285-11297, 2020 | 508* | 2020 |
| Hat: Hardware-aware transformers for efficient natural language processing H Wang, Z Wu, Z Liu, H Cai, L Zhu, C Gan, S Han arXiv preprint arXiv:2005.14187, 2020 | 377 | 2020 |
| On-device training under 256kb memory J Lin, L Zhu, WM Chen, WC Wang, C Gan, S Han Advances in Neural Information Processing Systems 35, 22941-22954, 2022 | 352 | 2022 |
| Longvila: Scaling long-context visual language models for long videos Y Chen, F Xue, D Li, Q Hu, L Zhu, X Li, Y Fang, H Tang, S Yang, Z Liu, ... arXiv preprint arXiv:2408.10188, 2024 | 191 | 2024 |
| Vila-u: a unified foundation model integrating visual understanding and generation Y Wu, Z Zhang, J Chen, H Tang, D Li, Y Fang, L Zhu, E Xie, H Yin, L Yi, ... arXiv preprint arXiv:2409.04429, 2024 | 188 | 2024 |
| Tiny machine learning: Progress and futures [feature] J Lin, L Zhu, WM Chen, WC Wang, S Han IEEE Circuits and Systems Magazine 23 (3), 8-34, 2023 | 188 | 2023 |
| Enable deep learning on mobile devices: Methods, systems, and applications H Cai, J Lin, Y Lin, Z Liu, H Tang, H Wang, L Zhu, S Han ACM Transactions on Design Automation of Electronic Systems (TODAES) 27 (3 …, 2022 | 187 | 2022 |
| Sana: Efficient high-resolution image synthesis with linear diffusion transformers E Xie, J Chen, J Chen, H Cai, H Tang, Y Lin, Z Zhang, M Li, L Zhu, Y Lu, ... arXiv preprint arXiv:2410.10629, 2024 | 154 | 2024 |
| Nvila: Efficient frontier visual language models Z Liu, L Zhu, B Shi, Z Zhang, Y Lou, S Yang, H Xi, S Cao, Y Gu, D Li, X Li, ... Proceedings of the Computer Vision and Pattern Recognition Conference, 4122-4134, 2025 | 111 | 2025 |
| Fast-dllm: Training-free acceleration of diffusion llm by enabling kv cache and parallel decoding C Wu, H Zhang, S Xue, Z Liu, S Diao, L Zhu, P Luo, S Han, E Xie arXiv preprint arXiv:2505.22618, 2025 | 99 | 2025 |
| Delayed gradient averaging: Tolerate the communication latency for federated learning L Zhu, H Lin, Y Lu, Y Lin, S Han Advances in neural information processing systems 34, 29995-30007, 2021 | 96 | 2021 |
| Ios: Inter-operator scheduler for cnn acceleration Y Ding, L Zhu, Z Jia, G Pekhimenko, S Han Proceedings of Machine Learning and Systems 3, 167-180, 2021 | 95 | 2021 |
| Sparsely aggregated convolutional networks L Zhu, R Deng, M Maire, Z Deng, G Mori, P Tan Proceedings of the European Conference on Computer Vision (ECCV), 186-201, 2018 | 85 | 2018 |
| Sana 1.5: Efficient scaling of training-time and inference-time compute in linear diffusion transformer E Xie, J Chen, Y Zhao, J Yu, L Zhu, C Wu, Y Lin, Z Zhang, M Li, J Chen, ... arXiv preprint arXiv:2501.18427, 2025 | 74 | 2025 |
| Automl for architecting efficient and specialized neural networks H Cai, J Lin, Y Lin, Z Liu, K Wang, T Wang, L Zhu, S Han IEEE Micro 40 (1), 75-82, 2019 | 66* | 2019 |
| SANA: Efficient high-resolution text-to-image synthesis with linear diffusion transformers E Xie, J Chen, J Chen, H Cai, H Tang, Y Lin, Z Zhang, M Li, L Zhu, Y Lu, ... The Thirteenth International Conference on Learning Representations, 2025 | 65 | 2025 |
| Thop: Pytorch-opcounter L Zhu THOP: PyTorch-OpCounter 11, 2022 | 60 | 2022 |
| Datamix: Efficient privacy-preserving edge-cloud inference Z Liu, Z Wu, C Gan, L Zhu, S Han European Conference on Computer Vision, 578-595, 2020 | 56 | 2020 |
Song HanMassachusetts Institute of TechnologyVerified email at mit.edu
