🧑‍🔬 Samuel L Smith

🏛️ Affiliations

🏥MedStar Franklin Square Medical CenterBaltimore · United States2008–2017 · 19 papers🏥Sinai HospitalBaltimore · United States1989–1997 · 13 papers🎓James Cook UniversityTownsville · Australia2012–2022 · 10 papersEducation since 2014 · MBBS (Hons.), College of Medicine and DentistryEducation since 2017 · Master of Public Health & Tropical MedicineEmployment · Anatomy Tutor, Discipline of Anatomy & Pathology🏥Royal Brisbane and Women's HospitalBrisbane · Australia2020–2024 · 9 papersEmployment · Doctor🏢Google DeepMindLondon · United Kingdom2018–2023 · 7 papers🎓The University of QueenslandBrisbane · Australia2021–2024 · 6 papers🎓University of CambridgeCambridge · United Kingdom2013–2019 · 6 papers🏥MedStar Harbor HospitalBaltimore · United States2015–2017 · 6 papers🏢GoogleMountain View · United States2017–2021 · 5 papers🎓University of BirminghamBirmingham · United Kingdom2017–2019 · 4 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 31 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.

📅 Works by year

2020s

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. Offline bilingual word vectors, orthogonal transformations and the inverted softmax (2017 · 435 citations)
   The paper studies how to build bilingual word embeddings "offline": two monolingual vector spaces are trained separately and then aligned with a mapping learned from a translation dictionary, following Mikolov et al.
2. Resurrecting Recurrent Neural Networks for Long Sequences (2023 · 118 citations)
   Classic RNNs are cheap at inference on long inputs, but they train slowly and suffer from vanishing or exploding gradients.

All works

8 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. Gemma: Open Models Based on Gemini Research and Technology ↗arXiv:2403.08295 · no summary yetGemma Team et al.2024 · 1,313 citations
2. Don't Decay the Learning Rate, Increase the Batch Size ↗arXiv:1711.00489 · no summary yetSamuel L. Smith et al.2017 · 680 citations
3. Offline bilingual word vectors, orthogonal transformations and the inverted softmaxarXiv:1702.03859Samuel L. Smith, David H. P. Turban, Steven Hamblin, et al.2017 · 435 citations
4. Resurrecting Recurrent Neural Networks for Long SequencesarXiv:2303.06349Antonio Orvieto, Samuel L Smith, Albert Gu, et al.2023 · 118 citations
5. A Bayesian Perspective on Generalization and Stochastic Gradient Descent ↗arXiv (Cornell University) · no summary yetSamuel L. Smith, Quoc Viet Le2017 · 51 citations
6. RecurrentGemma: Moving Past Transformers for Efficient Open Language Models ↗arXiv (Cornell University) · no summary yetAleksandar Botev et al.2024 · 22 citations
7. The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study ↗arXiv (Cornell University) · no summary yetDaniel Park et al.2019 · 13 citations
8. Stochastic natural gradient descent draws posterior samples in function space ↗arXiv (Cornell University) · no summary yetSamuel L. Smith et al.2018 · 2 citations

🤝 Co-authors here

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

• Albert Gu
• Antonio Orvieto
• Caglar Gulcehre
• Razvan Pascanu

🔗 Cited by

Papers of our library cite their works 1,513 times (of the 149,439 papers whose bibliographies we read); 287 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/samuel-l-smith/