🧑‍🔬 Danilo Jimenez Rezende

🏛️ Affiliations

🏢Google DeepMindLondon · United Kingdom2012–2024 · 34 papersEmployment since 2014current🏢GoogleMountain View · United States2015–2020 · 21 papers🔬Centre de Physique ThéoriqueMarseille · France2008–2009 · 3 papers🏢GoogleLondon · United Kingdom2016–2023 · 2 papers🎓Massachusetts Institute of TechnologyCambridge · United States2022–2023 · 2 papers🎓École Polytechnique Fédérale de LausanneLausanne · Switzerland2011–2014 · 2 papersEducation until 2013

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 7 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

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. Stochastic Backpropagation and Approximate Inference in Deep Generative Models (2014 · 2,765 citations)
   The paper addresses a long-standing difficulty with deep directed generative models: sampling from them is easy, but inferring their hidden variables efficiently has been hard.
2. Variational Inference with Normalizing Flows (2015 · 1,441 citations)
   Variational inference usually relies on simple posterior families, such as mean-field or diagonal Gaussians, so the approximation can never match the true posterior.
3. DRAW: A Recurrent Neural Network For Image Generation (2015 · 947 citations)
   Most neural generative models of images produce the whole picture in one step from a single latent code. This makes self-correction impossible and scales poorly to large images. DRAW (Deep Recurrent Attentive Writer), from Google DeepMind, instead builds an image gradually, much as a person sketches and then refines.…

All works

13 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. Stochastic Backpropagation and Approximate Inference in Deep Generative ModelsarXiv:1401.4082Danilo Jimenez Rezende, Shakir Mohamed, Daan Wierstra2014 · 2,765 citations
2. Semi-Supervised Learning with Deep Generative Models ↗UvA-DARE (University of Amsterdam) · no summary yetDiederik P. Kingma et al.2014 · 1,550 citations
3. Variational Inference with Normalizing FlowsDanilo Jimenez Rezende, Shakir Mohamed2015 · 1,441 citations
4. DRAW: A Recurrent Neural Network For Image GenerationarXiv:1502.04623Karol Gregor, Ivo Danihelka, Alex Graves, et al.2015 · 947 citations
5. Interaction Networks for Learning about Objects, Relations and Physics ↗arXiv:1612.00222 · no summary yetPeter W. Battaglia et al.2016 · 581 citations
6. Neural scene representation and rendering ↗Science · no summary yetS. M. Ali Eslami et al.2018 · 518 citations
7. Imagination-Augmented Agents for Deep Reinforcement Learning ↗arXiv (Cornell University) · no summary yetThéophane Weber et al.2017 · 241 citations
8. Unsupervised Predictive Memory in a Goal-Directed Agent ↗arXiv (Cornell University) · no summary yetGreg Wayne et al.2018 · 140 citations
9. Towards Conceptual Compression ↗neural information processing systems · no summary yetKarol Gregor et al.2016 · 118 citations
10. Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving ↗arXiv:2405.12205 · no summary yetAniket Didolkar et al.2024 · 45 citations
11. Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions ↗arXiv (Cornell University) · no summary yetScott Reed et al.2017 · 43 citations
12. A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities ↗arXiv (Cornell University) · no summary yetSimon Köhl et al.2019 · 23 citations
13. Towards Principled Unsupervised Learning ↗arXiv (Cornell University) · no summary yetIlya Sutskever et al.2015 · 21 citations

🤝 Co-authors here

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

• Daan Wierstra ×2
• Shakir Mohamed ×2
• Alex Graves

Venues

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

• Science
• UvA-DARE (University of Amsterdam)
• neural information processing systems

🔗 Cited by

Papers of our library cite their works 994 times (of the 149,439 papers whose bibliographies we read); 73 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/danilo-jimenez-rezende/