--- title: "Jason D. Lee · Princeton University — author profile and papers" description: "Jason D. Lee, Princeton University: 3 papers on Elamur Research (2023–2024), h-index 38 — affiliations, topics, co-authors and who cites…" canonical: "https://research.elamur.ai/free/en/authors/jason-d-lee/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/jason-d-lee/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Jason D. Lee # Jason D. Lee Jason D. Lee has 3 papers in our library, in 2023–2024, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/); often with [Danqi Chen](https://md.research.elamur.ai/free/en/authors/danqi-chen/), [Deming Chen](https://md.research.elamur.ai/free/en/authors/deming-chen/), [Kangwook Lee](https://md.research.elamur.ai/free/en/authors/kangwook-lee/). 3 papers in our library · 2023–2024 [OpenAlex](https://openalex.org/A5059740024) · [ORCID](https://orcid.org/0000-0003-0064-7800) · [**h-index 38**](https://openalex.org/authors/A5059740024) · [211 works](https://openalex.org/works?filter=author.id:A5059740024) · [5,770 citations](https://openalex.org/works?filter=author.id:A5059740024&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 3 works in our library](https://md.research.elamur.ai/free/en/authors/jason-d-lee/#papers) · [🔗 Cited 497 times in our library](https://md.research.elamur.ai/free/en/authors/jason-d-lee/cited-by/) · [3 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #4301](https://md.research.elamur.ai/free/en/paper-stars/page/44/#star-4301) 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=Jason+D.+Lee) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Jason+D.+Lee) · [dblp](https://dblp.org/search?q=Jason+D.+Lee) · [ACL Anthology](https://aclanthology.org/search/?q=Jason+D.+Lee) ## Affiliations [🎓**Princeton University** Princeton · United States 2018–2026 · 91 papers*current*](https://md.research.elamur.ai/free/en/universities/princeton-university/) · [🎓**University of California, Berkeley** Berkeley · United States 2015–2026 · 21 papersEducation 2015–2016 · Postdoc, Computer ScienceEmployment since 2025 · Associate Professor, EECS and Statistics*current*](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/) · [🎓**University of Southern California** Los Angeles · United States 2016–2020 · 26 papersEmployment 2016–2019 · Assistant Professor, Departments of Data Science & Operations and Computer Science](https://md.research.elamur.ai/free/en/universities/university-of-southern-california/) · [🎓**Stanford University** Stanford · United States 2012–2018 · 15 papersEducation until 2015 · PhD, Computational Math](https://md.research.elamur.ai/free/en/universities/stanford-university/) · [🎓**Duke University** Durham · United States 2009–2012 · 3 papersEducation until 2010 · BS, Mathematics](https://md.research.elamur.ai/free/en/universities/duke-university/) · [🎓**University of Washington** Seattle · United States 2020–2021 · 2 papers](https://md.research.elamur.ai/free/en/universities/university-of-washington/) · [🎓**Dartmouth College** Hanover · United States 2016 · 2 papers](https://md.research.elamur.ai/free/en/universities/dartmouth-college/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 8 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).[Arts and Humanities · 3 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Computer Science · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Language and Linguistics · 3 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Computer Vision and Pattern Recognition · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) 🧭 Topics 1 Research subjects and languages the work is about.[Language models & pretraining · 2 works](https://md.research.elamur.ai/free/en/topics/language-models/) ## Works by year ### 2020s [**2024** 1 paper](https://md.research.elamur.ai/free/en/authors/jason-d-lee/year/2024/) · [**2023** 2 papers](https://md.research.elamur.ai/free/en/authors/jason-d-lee/year/2023/) ## Papers The most cited first (OpenAlex and our library). 1. **[Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://md.research.elamur.ai/free/en/papers/cai-2024-medusa-simple-llm-inference-acceleration/)** *(2024 · 278 citations)* Generating text with an LLM is slow because tokens come out one at a time. Each step has to read all of the model's weights from HBM, so the accelerator spends most of its time waiting on memory rather than computing. Speculative decoding helps, but it needs a separate draft model, which is costly to obtain and… 2. **[Fine-Tuning Language Models with Just Forward Passes](https://md.research.elamur.ai/free/en/papers/malladi-2023-fine-tuning-language-models-just/)** *(2023 · 153 citations)* Fine-tuning large language models with backpropagation is memory-hungry. Activations, gradients and Adam's optimizer state can need roughly an order of magnitude more GPU memory than inference alone. The authors revisit zeroth-order optimization, which estimates gradients from loss differences rather than backward… 3. **[Teaching Arithmetic to Small Transformers](https://md.research.elamur.ai/free/en/papers/lee-2023-teaching-arithmetic-small-transformers/)** *(2023 · 57 citations)* The paper asks which factors let a next-token predictor acquire arithmetic. It uses a controlled setting: small decoder-only transformers (NanoGPT and GPT-2, from 10.6M up to 124M parameters) trained from random initialization with character-level tokens. Tasks include addition, subtraction, multiplication, square… ## All works 6 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them. 1. [**Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads arXiv:2401.10774**Tianle Cai, Yuhong Li, Zhengyang Geng, et al.*2024 · 278 citations*](https://md.research.elamur.ai/free/en/papers/cai-2024-medusa-simple-llm-inference-acceleration/) 2. **[Fine-Tuning Language Models with Just Forward Passes](https://md.research.elamur.ai/free/en/papers/malladi-2023-fine-tuning-language-models-just/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Sadhika Malladi, Tianyu Gao, Eshaan Nichani, et al.*2023 · 153 citations* 3. [**Teaching Arithmetic to Small Transformers arXiv:2307.03381**Nayoung Lee, Kartik Sreenivasan, Jason D. Lee, et al.*2023 · 57 citations*](https://md.research.elamur.ai/free/en/papers/lee-2023-teaching-arithmetic-small-transformers/) 4. **[On the Convergence and Robustness of Training GANs with Regularized Optimal Transport ↗](https://arxiv.org/abs/1802.08249) arXiv (Cornell University) · no summary yet**Maziar Sanjabi et al.*2018 · 57 citations* 5. **[Towards Understanding Hierarchical Learning: Benefits of Neural Representations ↗](https://arxiv.org/abs/2006.13436) arXiv (Cornell University) · no summary yet**Minshuo Chen et al.*2020 · 17 citations* 6. **[Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation ↗](https://arxiv.org/abs/2502.01694) arXiv:2502.01694 · no summary yet**Juno Kim et al.*2025 · 6 citations* ## Co-authors here 9 co-authors with a page, the most papers together first. - [Danqi Chen](https://md.research.elamur.ai/free/en/authors/danqi-chen/) - [Deming Chen](https://md.research.elamur.ai/free/en/authors/deming-chen/) - [Kangwook Lee](https://md.research.elamur.ai/free/en/authors/kangwook-lee/) - [Sadhika Malladi](https://md.research.elamur.ai/free/en/authors/sadhika-malladi/) - [Sanjeev Arora](https://md.research.elamur.ai/free/en/authors/sanjeev-arora/) - [Tianle Cai](https://md.research.elamur.ai/free/en/authors/tianle-cai/) - [Tianyu Gao](https://md.research.elamur.ai/free/en/authors/tianyu-gao/) - [Tri Dao](https://md.research.elamur.ai/free/en/authors/tri-dao/) - [Yuhong Li](https://md.research.elamur.ai/free/en/authors/yuhong-li/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/): [NeurIPS 2023](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2023/) ## Cited by Papers of our library cite their works 497 times (of the 149,439 papers whose bibliographies we read); [69 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/jason-d-lee/cited-by/). Updated 2 November 2026