--- title: "Natalia Gimelshein · OpenAI — author profile and papers" description: "Natalia Gimelshein, OpenAI: 4 papers on Elamur Research (2016–2024), h-index 18 — affiliations, topics, co-authors and who cites them in…" canonical: "https://research.elamur.ai/free/en/authors/natalia-gimelshein/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/natalia-gimelshein/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Natalia Gimelshein # Natalia Gimelshein Natalia Gimelshein has 4 papers in our library, in 2016–2024, most of them on [Efficient models & compression](https://md.research.elamur.ai/free/en/topics/efficient-models/); often with [Adam K. Lerer](https://md.research.elamur.ai/free/en/authors/adam-k-lerer/), [Adam Paszke](https://md.research.elamur.ai/free/en/authors/adam-paszke/), [Andreas Köpf](https://md.research.elamur.ai/free/en/authors/andreas-kopf/). 4 papers in our library · 2016–2024 [OpenAlex](https://openalex.org/A5078016863) · [ORCID](https://orcid.org/0009-0002-9867-5075) · [Wikidata](https://www.wikidata.org/wiki/Q130845951) · [**h-index 18**](https://openalex.org/authors/A5078016863) · [73 works](https://openalex.org/works?filter=author.id:A5078016863) · [16,885 citations](https://openalex.org/works?filter=author.id:A5078016863&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 4 works in our library](https://md.research.elamur.ai/free/en/authors/natalia-gimelshein/#papers) · [🔗 Cited 4,163 times in our library](https://md.research.elamur.ai/free/en/authors/natalia-gimelshein/cited-by/) · [⭐ Paper Stars ranking: #138](https://md.research.elamur.ai/free/en/paper-stars/page/2/#star-138) 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=Natalia+Gimelshein) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Natalia+Gimelshein) · [dblp](https://dblp.org/search?q=Natalia+Gimelshein) · [ACL Anthology](https://aclanthology.org/search/?q=Natalia+Gimelshein) ## Affiliations [🏢**OpenAI** San Francisco · United States 2024 · 1 paper*current*](https://md.research.elamur.ai/free/en/companies/openai/) · [🔬**Edwards Air Force Base** Edwards Air Force Base · United States 2007–2014 · 26 papers](https://ror.org/0079vgv93) · [🎓**Pennsylvania State University** State College · United States 2001–2008 · 10 papers](https://md.research.elamur.ai/free/en/universities/pennsylvania-state-university/) · [🏢**ERC Inc.** Imizu Shi · Japan 2007–2013 · 8 papers](https://ror.org/02hhnp155) · [🏢**Nvidia** Santa Clara · United States 2016–2018 · 4 papers](https://md.research.elamur.ai/free/en/companies/nvidia/) · [🔬**United States Air Force Research Laboratory** Wright-Patterson AFB · United States 2008–2010 · 2 papers](https://md.research.elamur.ai/free/en/labs/united-states-air-force-research-laboratory/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 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 6 The field of science this work belongs to (OpenAlex fields).[Computer Science · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Computer Vision and Pattern Recognition · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Hardware and Architecture · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/hardware-and-architecture/) · [Artificial Intelligence · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Computational Theory and Mathematics · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computational-theory-and-mathematics/) · [Information Systems · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) 🧭 Topics 1 Research subjects and languages the work is about.[Efficient models & compression · 1 work](https://md.research.elamur.ai/free/en/topics/efficient-models/) 💡 Concepts 2 Key ideas and methods explained on our concept pages.[Machine learning · 1 work](https://md.research.elamur.ai/free/en/concepts/machine-learning/) · [Latent semantic indexing · 1 work](https://md.research.elamur.ai/free/en/concepts/latent-semantic-indexing/) ## Works by year ### 2020s [**2024** 1 paper](https://md.research.elamur.ai/free/en/authors/natalia-gimelshein/year/2024/) ### 2010s [**2019** 1 paper](https://md.research.elamur.ai/free/en/authors/natalia-gimelshein/year/2019/) · [**2018** 1 paper](https://md.research.elamur.ai/free/en/authors/natalia-gimelshein/year/2018/) · [**2016** 1 paper](https://md.research.elamur.ai/free/en/authors/natalia-gimelshein/year/2016/) ## Papers The most cited first (OpenAlex and our library). 1. **[PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://md.research.elamur.ai/free/en/papers/paszke-2019-pytorch-imperative-style-high-performance/)** *(2019 · 18,645 citations)* Older deep learning frameworks usually made a trade: static dataflow graphs gave speed and global optimization but were hard to debug and inflexible, while eager define-by-run tools were either slow or tied to less expressive languages. 2. **[PyTorch 2: Faster Machine Learning Through Dynamic Python Bytecode Transformation and Graph Compilation](https://md.research.elamur.ai/free/en/papers/ansel-2024-pytorch-2-faster-machine-learning/)** *(2024 · 946 citations)* Eager-mode frameworks such as PyTorch are popular because models are plain Python code that can be debugged and mixed freely with other libraries. 3. **[Online normalizer calculation for softmax](https://md.research.elamur.ai/free/en/papers/milakov-2018-online-normalizer-calculation-softmax/)** *(2018 · 123 citations)* Softmax sits at the output of most language models. Many faster substitutes exist (hierarchical, sampling-based, SVD-based), but nearly all of them still run the exact softmax on some vector. This NVIDIA paper speeds up that exact function. The numerically safe variant used by TensorFlow, PyTorch, MXNET, Microsoft… 4. **[vDNN: Virtualized Deep Neural Networks for Scalable, Memory-Efficient Neural Network Design](https://md.research.elamur.ai/free/en/papers/rhu-2016-vdnn-virtualized-deep-neural-networks/)** *(2016 · 81 citations)* Training a deep network on a GPU normally requires the whole network's memory footprint to fit in GPU DRAM. ## Co-authors here 9 co-authors with a page, the most papers together first. - [Adam K. Lerer](https://md.research.elamur.ai/free/en/authors/adam-k-lerer/) - [Adam Paszke](https://md.research.elamur.ai/free/en/authors/adam-paszke/) - [Andreas Köpf](https://md.research.elamur.ai/free/en/authors/andreas-kopf/) - [Evgeni Burovski](https://md.research.elamur.ai/free/en/authors/evgeni-burovski/) - [Francisco Massa](https://md.research.elamur.ai/free/en/authors/francisco-massa/) - [Horace He](https://md.research.elamur.ai/free/en/authors/horace-he/) - [James Bradbury](https://md.research.elamur.ai/free/en/authors/james-bradbury/) - [Peter Bell](https://md.research.elamur.ai/free/en/authors/peter-bell/) - [Sam Gross](https://md.research.elamur.ai/free/en/authors/sam-gross/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - [ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)](https://md.research.elamur.ai/free/en/venues/acm-international-conference-on-architectural-support-for-programming-languages/): [ASPLOS 2024](https://md.research.elamur.ai/free/en/venues/acm-international-conference-on-architectural-support-for-programming-languages/2024/) - MICRO 2016 ## Cited by Papers of our library cite their works 4,163 times (of the 149,439 papers whose bibliographies we read); [335 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/natalia-gimelshein/cited-by/). Updated 2 November 2026