--- title: "Han Cai — author profile and papers · GPU & parallel computing" description: "Han Cai, Nvidia: 4 papers on Elamur Research (2017–2020), h-index 27 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/han-cai/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/han-cai/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Han Cai # Han Cai Han Cai has 4 papers in our library, in 2017–2020, most of them on [GPU & parallel computing](https://md.research.elamur.ai/free/en/topics/gpu-parallel-computing/); often with [Song Han](https://md.research.elamur.ai/free/en/authors/song-han/), [Chuang Gan](https://md.research.elamur.ai/free/en/authors/chuang-gan/), [Ligeng Zhu](https://md.research.elamur.ai/free/en/authors/ligeng-zhu/). 4 papers in our library · 2017–2020 [OpenAlex](https://openalex.org/A5087929301) · [ORCID](https://orcid.org/0000-0002-4906-1192) · [**h-index 27**](https://openalex.org/authors/A5087929301) · [114 works](https://openalex.org/works?filter=author.id:A5087929301) · [4,801 citations](https://openalex.org/works?filter=author.id:A5087929301&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 4 works in our library](https://md.research.elamur.ai/free/en/authors/han-cai/#papers) · [🔗 Cited 674 times in our library](https://md.research.elamur.ai/free/en/authors/han-cai/cited-by/) · [7 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #1870](https://md.research.elamur.ai/free/en/paper-stars/page/19/#star-1870) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Han+Cai) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Han+Cai) · [dblp](https://dblp.org/search?q=Han+Cai) · [ACL Anthology](https://aclanthology.org/search/?q=Han+Cai) ## Affiliations [🏢**Nvidia** Santa Clara · United States 2024–2026 · 11 papers*current*](https://md.research.elamur.ai/free/en/companies/nvidia/) · [🏢**Nvidia** Reading · United Kingdom 2024–2026 · 8 papers*current*](https://md.research.elamur.ai/free/en/companies/nvidia-united-kingdom/) · [🎓**Maryland Quantum Materials Center** College Park · United States *current*](https://ror.org/01bdy0k56) · [🎓**University of Maryland, College Park** College Park · United States Employment*current*](https://md.research.elamur.ai/free/en/universities/university-of-maryland-college-park/) · [🎓**Massachusetts Institute of Technology** Cambridge · United States 2019–2024 · 20 papers](https://md.research.elamur.ai/free/en/universities/massachusetts-institute-of-technology/) · [🎓**Shanghai Jiao Tong University** Shanghai · China 2016–2019 · 10 papers](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed. ## Fields, topics and concepts Of its works in our library, with the number of works on each. 📚 Shelves 5 The field of science this work belongs to (OpenAlex fields).[Computer Science · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Computer Vision and Pattern Recognition · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Arts and Humanities · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) 🧭 Topics 1 Research subjects and languages the work is about.[GPU & parallel computing · 2 works](https://md.research.elamur.ai/free/en/topics/gpu-parallel-computing/) ## Works by year ### 2020s [**2020** 1 paper](https://md.research.elamur.ai/free/en/authors/han-cai/year/2020/) ### 2010s [**2019** 1 paper](https://md.research.elamur.ai/free/en/authors/han-cai/year/2019/) · [**2018** 1 paper](https://md.research.elamur.ai/free/en/authors/han-cai/year/2018/) · [**2017** 1 paper](https://md.research.elamur.ai/free/en/authors/han-cai/year/2017/) ## Papers The most cited first (OpenAlex and our library). 1. **[Efficient Architecture Search by Network Transformation](https://md.research.elamur.ai/free/en/papers/cai-2017-efficient-architecture-search-network-transformation/)** *(2017 · 629 citations)* Automated neural architecture search with reinforcement learning or evolution has matched human-designed models. 2. **[ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://md.research.elamur.ai/free/en/papers/cai-2018-proxylessnas-direct-neural-architecture-search/)** *(2018 · 479 citations)* Neural architecture search typically costs thousands of GPU hours. Differentiable variants such as DARTS and One-Shot are cheaper, but they keep the activations of every candidate operation in memory, so memory grows with the number of choices. As a result, earlier methods search on cheaper stand-ins, such as smaller… 3. **[HAT: Hardware-Aware Transformers for Efficient Natural Language Processing](https://md.research.elamur.ai/free/en/papers/wang-2020-hat-hardware-aware-transformers-efficient/)** *(2020 · 294 citations)* Transformer models for machine translation are too slow on constrained devices. For example, Transformer-Big needs about 13G FLOPs and roughly 20 seconds on a Raspberry Pi to translate a 30-word sentence. The authors make two observations: FLOPs poorly predict real latency, and the architecture that runs fastest… 4. **[Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://md.research.elamur.ai/free/en/papers/cai-2019-once-all-train-one-network/)** *(2019 · 252 citations)* Deploying neural networks across many devices (phones, CPUs, GPUs, FPGAs, microcontrollers) and latency budgets usually means designing or searching a new architecture and training it from scratch for each target, so the cost grows with every new scenario. ## All works 11 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them. 1. **[Efficient Architecture Search by Network Transformation](https://md.research.elamur.ai/free/en/papers/cai-2017-efficient-architecture-search-network-transformation/) [Proceedings of the AAAI Conference on Artificial Intelligence](https://md.research.elamur.ai/free/en/venues/proceedings-of-the-aaai-conference-on-artificial-intelligence/)**Han Cai, Tianyao Chen, Weinan Zhang, et al.*2017 · 629 citations* 2. [**ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware arXiv:1812.00332**Han Cai, Ligeng Zhu, Song Han*2018 · 479 citations*](https://md.research.elamur.ai/free/en/papers/cai-2018-proxylessnas-direct-neural-architecture-search/) 3. **[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* 4. **[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* 5. [**Once-for-All: Train One Network and Specialize it for Efficient Deployment arXiv:1908.09791**Han Cai, Chuang Gan, Tianzhe Wang, et al.*2019 · 252 citations*](https://md.research.elamur.ai/free/en/papers/cai-2019-once-all-train-one-network/) 6. **[MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence ↗](https://arxiv.org/abs/1712.00600) arXiv:1712.00600 · no summary yet**Lianmin Zheng et al.*2017 · 158 citations* 7. **[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* 8. **[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* 9. **[Cosmos 3: Omnimodal World Models for Physical AI ↗](https://arxiv.org/abs/2606.02800) arXiv (Cornell University) · no summary yet**NVIDIA et al.*2026 · 19 citations* 10. **[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* 11. **[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* ## Co-authors here 10 co-authors with a page, the most papers together first. - [Song Han](https://md.research.elamur.ai/free/en/authors/song-han/) ×3 - [Chuang Gan](https://md.research.elamur.ai/free/en/authors/chuang-gan/) ×2 - [Ligeng Zhu](https://md.research.elamur.ai/free/en/authors/ligeng-zhu/) ×2 - [Hanrui Wang](https://md.research.elamur.ai/free/en/authors/hanrui-wang/) - [Jun Wang](https://md.research.elamur.ai/free/en/authors/jun-wang/) - [Weinan Zhang](https://md.research.elamur.ai/free/en/authors/weinan-zhang/) - [Yong Yu](https://md.research.elamur.ai/free/en/authors/yong-yu/) - [Zhanghao Wu](https://md.research.elamur.ai/free/en/authors/zhanghao-wu/) - [Zhekai Zhang](https://md.research.elamur.ai/free/en/authors/zhekai-zhang/) - [Zhijian Liu](https://md.research.elamur.ai/free/en/authors/zhijian-liu/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/): [ACL 2020](https://md.research.elamur.ai/free/en/venues/acl/2020/) - [Proceedings of the AAAI Conference on Artificial Intelligence](https://md.research.elamur.ai/free/en/venues/proceedings-of-the-aaai-conference-on-artificial-intelligence/): [Proceedings of the AAAI Conference on Artificial Intelligence 2017](https://md.research.elamur.ai/free/en/venues/proceedings-of-the-aaai-conference-on-artificial-intelligence/2017/) - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE/CVF International Conference on Computer Vision (ICCV) ## Cited by Papers of our library cite their works 674 times (of the 149,439 papers whose bibliographies we read); [18 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/han-cai/cited-by/). Updated 2 November 2026