Elamur Research⌕
☰
home / authors / Natalia Gimelshein

Natalia Gimelshein

Natalia Gimelshein has 3 papers in our library, in 2018–2024; often with Adam K. Lerer, Adam Paszke, Andreas Köpf.

3 papers in our library · 2018–2024

OpenAlex · ORCID · Wikidata · h-index 18 · 73 works · 16,885 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 4,163 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #129

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🏢OpenAISan Francisco · United States2024 · 1 papercurrent🔬Edwards Air Force BaseEdwards Air Force Base · United States2007–2014 · 26 papers🎓Pennsylvania State UniversityState College · United States2001–2008 · 10 papers🏢ERC Inc.Imizu Shi · Japan2007–2013 · 8 papers🏢NvidiaSanta Clara · United States2016–2018 · 4 papers🔬United States Air Force Research LaboratoryWright-Patterson AFB · United States2008–2010 · 2 papers

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 5The field of science this work belongs to (OpenAlex fields).Computer Science · 3 worksComputer Vision and Pattern Recognition · 3 worksHardware and Architecture · 3 worksArtificial Intelligence · 2 worksComputational Theory and Mathematics · 1 work

💡 Concepts 2Key ideas and methods explained on our concept pages.Machine learning · 1 workLatent semantic indexing · 1 work

 Works by year

2020s

20241 paper

2010s

20191 paper20181 paper

 Papers

The most cited first (OpenAlex and our library).

  1. PyTorch: An Imperative Style, High-Performance Deep Learning Library (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 (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 (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…

All works

4 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. PyTorch: An Imperative Style, High-Performance Deep Learning LibraryarXiv:1912.01703Adam Paszke, Sam Gross, Francisco Massa, et al.2019 · 18,645 citations
  2. PyTorch 2: Faster Machine Learning Through Dynamic Python Bytecode Transformation and Graph CompilationASPLOS 2024Jason Ansel, Edward Yang, Horace He, et al.2024 · 946 citations
  3. Online normalizer calculation for softmaxarXiv 2018 (NVIDIA)Maxim Milakov, Natalia Gimelshein2018 · 123 citations
  4. vDNN: Virtualized Deep Neural Networks for Scalable, Memory-Efficient Neural Network Design ↗MICRO 2016 · no summary yetMinsoo Rhu et al.2016 · 81 citations

 Co-authors here

9 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 4,163 times (of the 149,439 papers whose bibliographies we read); 285 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/natalia-gimelshein/