🧑‍🔬 Daniel Tarlow

🏛️ Affiliations

🏢GoogleMountain View · United States2019–2024 · 17 paperscurrent🏢MicrosoftRedmond · United States2013–2017 · 18 papers🎓University of TorontoToronto · Canada2006–2015 · 18 papers🏢Microsoft ResearchCambridge · United Kingdom2013–2017 · 6 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 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. Structured Denoising Diffusion Models in Discrete State-Spaces (2021 · 284 citations)
   Most diffusion generative models rely on continuous Gaussian noise. That fits images and audio but not inherently discrete data such as text or quantized pixels. Earlier discrete versions spread corruption uniformly across categories and had not proven competitive at scale. The authors (Google Research) propose D3PMs…
2. Bimodal Modelling of Source Code and Natural Language (2015 · 179 citations)
   The authors build a probabilistic model that jointly describes short natural-language phrases and fragments of source code.

All works

19 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. Gated Graph Sequence Neural Networks ↗arXiv:1511.05493 · no summary yetYujia Li et al.2015 · 576 citations
2. Structured Denoising Diffusion Models in Discrete State-SpacesarXiv:2107.03006Jacob Austin, Daniel D. Johnson, Jonathan Ho, et al.2021 · 284 citations
3. Bimodal Modelling of Source Code and Natural LanguageICML 2015, PMLR 37:2123–2132Miltos Allamanis, Daniel Tarlow, Andrew Gordon, et al.2015 · 179 citations
4. HOP-MAP: Efficient Message Passing with High Order Potentials ↗International Conference on Artificial Intelligence and Statistics · no summary yetDaniel Tarlow, Inmar E. Givoni, Richard S. Zemel2010 · 114 citations
5. Fits Like a Glove: Rapid and Reliable Hand Shape Personalization ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetDavid Joseph Tan et al.2016 · 85 citations
6. Graph Partition Neural Networks for Semi-Supervised Classification ↗arXiv (Cornell University) · no summary yetRenjie Liao et al.2018 · 55 citations
7. Learning Articulated Structure and Motion ↗International Journal of Computer Vision · no summary yetDavid A. Ross, Daniel Tarlow, Richard S. Zemel2010 · 49 citations
8. Structured Output Learning with High Order Loss Functions ↗no summary yetDaniel Tarlow, Richard S. Zemel2012 · 45 citations
9. Exploring Compositional High Order Pattern Potentials for Structured Output Learning ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetYujia Li, Daniel Tarlow, Richard S. Zemel2013 · 33 citations
10. Stochastic k-Neighborhood Selection for Supervised and Unsupervised Learning ↗no summary yetDaniel Tarlow et al.2013 · 30 citations
11. Fast Exact Inference for Recursive Cardinality Models ↗arXiv (Cornell University) · no summary yetDaniel Tarlow et al.2012 · 27 citations
12. Flexible Priors for Exemplar-based Clustering ↗arXiv (Cornell University) · no summary yetDaniel Tarlow, Richard S. Zemel, Brendan J. Frey2012 · 21 citations
13. Unsupervised Learning of Skeletons from Motion ↗Lecture notes in computer science · no summary yetDavid A. Ross, Daniel Tarlow, Richard S. Zemel2008 · 18 citations
14. Graph cuts is a max-product algorithm ↗no summary yetDaniel Tarlow et al.2011 · 17 citations
15. Interpreting Graph Cuts as a Max-Product Algorithm ↗arXiv (Cornell University) · no summary yetDaniel Tarlow et al.2011 · 3 citations
16. Learning Articulated Skeletons from Motion ↗no summary yetDavid A. Ross, Daniel Tarlow, Richard S. Zemel2007 · 3 citations
17. Under review as a conference paper at ICLR 2016 GATED GRAPH SEQUENCE NEURAL NETWORKS ↗no summary yetYujia Li et al.2016
18. Factorizing Shortest Paths with Randomized Optimum Models ↗The MIT Press eBooks · no summary yetDaniel Tarlow et al.2016
19. Exploring Compositional High Order Pattern Potentials for Structured Output Learning Supplementary Material ↗no summary yetYujia Li, Daniel Tarlow, Rich Zemel2013

🤝 Co-authors here

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

• Andrew Gordon
• Jacob Austin
• Jonathan Ho

Venues

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

• IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings ×2
• ICML 2015, PMLR 37:2123–2132
• International Conference on Artificial Intelligence and Statistics
• International Journal of Computer Vision
• Lecture notes in computer science
• The MIT Press eBooks

🔗 Cited by

Papers of our library cite their works 466 times (of the 149,439 papers whose bibliographies we read); 79 citing papers with a page here →.

Updated 3 November 2026

↑ back to top

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