---
title: "Razvan Pascanu — author profile and papers · Reasoning"
description: "Razvan Pascanu, Google DeepMind: 5 papers on Elamur Research (2012–2023), h-index 54 — affiliations, topics, co-authors and who cites…"
canonical: "https://research.elamur.ai/free/en/authors/razvan-pascanu/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/razvan-pascanu/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Razvan Pascanu

# Razvan Pascanu

Razvan Pascanu has 5 papers in our library, in 2012–2023, most of them on [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/); often with [Caglar Gulcehre](https://md.research.elamur.ai/free/en/authors/caglar-gulcehre/), [Yoshua Bengio](https://md.research.elamur.ai/free/en/authors/yoshua-bengio/), [Adam Santoro](https://md.research.elamur.ai/free/en/authors/adam-santoro/).

5 papers in our library · 2012–2023

[OpenAlex](https://openalex.org/A5043910056) · [ORCID](https://orcid.org/0000-0002-5470-1238) · [Wikidata](https://www.wikidata.org/wiki/Q47012846) · [**h-index 54**](https://openalex.org/authors/A5043910056) · [211 works](https://openalex.org/works?filter=author.id:A5043910056) · [30,541 citations](https://openalex.org/works?filter=author.id:A5043910056&sort=cited_by_count:desc) OpenAlex, 2026-10-14

[📄 5 works in our library](https://md.research.elamur.ai/free/en/authors/razvan-pascanu/#papers) · [🔗 Cited 1,344 times in our library](https://md.research.elamur.ai/free/en/authors/razvan-pascanu/cited-by/) · [22 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #1344](https://md.research.elamur.ai/free/en/paper-stars/page/14/#star-1344)

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=Razvan+Pascanu) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Razvan+Pascanu) · [dblp](https://dblp.org/search?q=Razvan+Pascanu) · [ACL Anthology](https://aclanthology.org/search/?q=Razvan+Pascanu)

## Affiliations

[🏢**Google DeepMind** London · United Kingdom 2015–2026 · 41 papersEmployment*current*](https://md.research.elamur.ai/free/en/companies/google-deepmind/) · [🎓**Université de Montréal** Montreal · Canada 2010–2026 · 25 papersEducation until 2014*current*](https://md.research.elamur.ai/free/en/universities/universite-de-montreal/) · [🔬**Mila - Quebec Artificial Intelligence Institute** Montreal · Canada 2023–2026 · 4 papers*current*](https://md.research.elamur.ai/free/en/labs/mila-quebec-artificial-intelligence-institute/) · [🎓**Imperial College London** London · United Kingdom 2020–2026 · 2 papers*current*](https://md.research.elamur.ai/free/en/universities/imperial-college-london/) · [🏢**Google** Mountain View · United States 2015–2025 · 35 papers](https://md.research.elamur.ai/free/en/companies/google/) · [🏢**Google** London · United Kingdom 2018–2024 · 3 papersEmployment](https://md.research.elamur.ai/free/en/companies/google-united-kingdom/) · [🎓**Stanford University** Stanford · United States 2021–2025 · 2 papers](https://md.research.elamur.ai/free/en/universities/stanford-university/) · [🎓**ETH Zurich** Zurich · Switzerland 2023–2024 · 2 papers](https://md.research.elamur.ai/free/en/universities/eth-zurich/) · [🎓**University of Oxford** Oxford · United Kingdom 2019–2022 · 2 papers](https://md.research.elamur.ai/free/en/universities/university-of-oxford/) · [🎓**Washington State University** Pullman · United States 2021–2022 · 2 papers](https://ror.org/05dk0ce17)

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.

📚 Shelves 6 The field of science this work belongs to (OpenAlex fields).[Computer Science · 5 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 5 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 3 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Computer Vision and Pattern Recognition · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Language and Linguistics · 3 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Hardware and Architecture · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/hardware-and-architecture/)

🧭 Topics 1 Research subjects and languages the work is about.[Reasoning · 1 work](https://md.research.elamur.ai/free/en/topics/reasoning/)

## Works by year

### 2020s

[**2023** 1 paper](https://md.research.elamur.ai/free/en/authors/razvan-pascanu/year/2023/)

### 2010s

[**2018** 1 paper](https://md.research.elamur.ai/free/en/authors/razvan-pascanu/year/2018/) · [**2017** 1 paper](https://md.research.elamur.ai/free/en/authors/razvan-pascanu/year/2017/) · [**2013** 1 paper](https://md.research.elamur.ai/free/en/authors/razvan-pascanu/year/2013/) · [**2012** 1 paper](https://md.research.elamur.ai/free/en/authors/razvan-pascanu/year/2012/)

## Papers

The most cited first (OpenAlex and our library).

1. **[Theano: new features and speed improvements](https://md.research.elamur.ai/free/en/papers/bastien-2012-theano-new-features-speed-improvements/)** *(2012 · 1,111 citations)* This 2012 report describes how Theano, a Python-based compiler that turns symbolic linear-algebra expressions into optimized CPU or GPU code, was extended and made faster.
2. **[A simple neural network module for relational reasoning](https://md.research.elamur.ai/free/en/papers/santoro-2017-simple-neural-network-module-relational/)** *(2017 · 632 citations)* Networks such as CNNs and MLPs often fail on questions that depend on how several entities relate. Symbolic systems handle relations well but are brittle and hard to ground in raw input. The authors propose the Relation Network (RN), a small, fully differentiable module. It takes a set of "objects," applies one…
3. **[Progress & Compress: A scalable framework for continual learning](https://md.research.elamur.ai/free/en/papers/schwarz-2018-progress-compress-scalable-framework-continual/)** *(2018 · 338 citations)* Neural networks that learn tasks one after another tend to lose earlier skills, a problem called catastrophic forgetting.
4. **[How to Construct Deep Recurrent Neural Networks](https://md.research.elamur.ai/free/en/papers/pascanu-2013-construct-deep-recurrent-neural-networks/)** *(2013 · 302 citations)* In feedforward networks, depth means stacking nonlinear layers between input and output. In recurrent networks the idea is ambiguous: an RNN unrolled over time is already deep, yet each single step uses only an affine map followed by an elementwise nonlinearity. Pascanu, Gulcehre, Cho and Bengio examine one step of…
5. **[Resurrecting Recurrent Neural Networks for Long Sequences](https://md.research.elamur.ai/free/en/papers/orvieto-2023-resurrecting-recurrent-neural-networks-long/)** *(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

27 works of theirs in our library, the most cited first; 5 with a page here, the others link their original until we summarise them.

1. **[Progressive Neural Networks ↗](https://arxiv.org/abs/1606.04671) arXiv:1606.04671 · no summary yet**Andrei A. Rusu et al.*2016 · 1,295 citations*
2. [**Theano: new features and speed improvements arXiv:1211.5590**Frédéric Bastien, Pascal Lamblin, Razvan Pascanu, et al.*2012 · 1,111 citations*](https://md.research.elamur.ai/free/en/papers/bastien-2012-theano-new-features-speed-improvements/)
3. **[Identifying and attacking the saddle point problem in high-dimensional non-convex optimization ↗](https://arxiv.org/abs/1406.2572) arXiv (Cornell University) · no summary yet**Yann Dauphin et al.*2014 · 818 citations*
4. **[On the Number of Linear Regions of Deep Neural Networks ↗](https://arxiv.org/abs/1402.1869) arXiv (Cornell University) · no summary yet**Guido Montúfar et al.*2014 · 811 citations*
5. [**A simple neural network module for relational reasoning arXiv:1706.01427**Adam Santoro, David Raposo, David G. T. Barrett, et al.*2017 · 632 citations*](https://md.research.elamur.ai/free/en/papers/santoro-2017-simple-neural-network-module-relational/)
6. **[Interaction Networks for Learning about Objects, Relations and Physics ↗](https://arxiv.org/abs/1612.00222) arXiv:1612.00222 · no summary yet**Peter W. Battaglia et al.*2016 · 581 citations*
7. **[Learning Deep Generative Models of Graphs ↗](https://arxiv.org/abs/1803.03324) arXiv (Cornell University) · no summary yet**Yujia Li et al.*2018 · 422 citations*
8. **[Learning to Navigate in Complex Environments ↗](https://arxiv.org/abs/1611.03673) arXiv (Cornell University) · no summary yet**Piotr Mirowski et al.*2016 · 366 citations*
9. [**Progress & Compress: A scalable framework for continual learning arXiv:1805.06370**Jonathan Schwarz, Jelena Luketina, Wojciech M. Czarnecki, et al.*2018 · 338 citations*](https://md.research.elamur.ai/free/en/papers/schwarz-2018-progress-compress-scalable-framework-continual/)
10. [**How to Construct Deep Recurrent Neural Networks arXiv:1312.6026**Razvan Pascanu, Caglar Gulcehre, Kyunghyun Cho, et al.*2013 · 302 citations*](https://md.research.elamur.ai/free/en/papers/pascanu-2013-construct-deep-recurrent-neural-networks/)
11. **[Imagination-Augmented Agents for Deep Reinforcement Learning ↗](https://arxiv.org/abs/1707.06203) arXiv (Cornell University) · no summary yet**Théophane Weber et al.*2017 · 241 citations*
12. **[Meta-Learning with Latent Embedding Optimization ↗](https://arxiv.org/abs/1807.05960) arXiv (Cornell University) · no summary yet**Andrei A. Rusu et al.*2018 · 213 citations*
13. **[Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks ↗](https://doi.org/10.1007/978-3-662-44848-9_34) Lecture notes in computer science · no summary yet**Çağlar Gülçehre et al.*2014 · 171 citations*
14. **[Relational Deep Reinforcement Learning ↗](https://arxiv.org/abs/1806.01830) arXiv (Cornell University) · no summary yet**Vinícius Zambaldi et al.*2018 · 160 citations*
15. **[Deep reinforcement learning with relational inductive biases ↗](https://openalex.org/W2907502844) International Conference on Learning Representations · no summary yet**Vinícius Zambaldi et al.*2018 · 132 citations*
16. **[Natural Neural Networks ↗](https://arxiv.org/abs/1507.00210) arXiv (Cornell University) · no summary yet**Desjardins, Guillaume et al.*2015 · 131 citations*
17. [**Resurrecting Recurrent Neural Networks for Long Sequences arXiv:2303.06349**Antonio Orvieto, Samuel L Smith, Albert Gu, et al.*2023 · 118 citations*](https://md.research.elamur.ai/free/en/papers/orvieto-2023-resurrecting-recurrent-neural-networks-long/)
18. **[Policy Distillation ↗](https://arxiv.org/abs/1511.06295) arXiv (Cornell University) · no summary yet**Andrei A. Rusu et al.*2015 · 108 citations*
19. **[Learning model-based planning from scratch ↗](https://arxiv.org/abs/1707.06170) arXiv (Cornell University) · no summary yet**Razvan Pascanu et al.*2017 · 76 citations*
20. **[Metacontrol for Adaptive Imagination-Based Optimization ↗](https://arxiv.org/abs/1705.02670) arXiv (Cornell University) · no summary yet**Jessica B. Hamrick et al.*2017 · 46 citations*
21. **[Relational recurrent neural networks ↗](https://arxiv.org/abs/1806.01822) arXiv (Cornell University) · no summary yet**Adam Santoro et al.*2018 · 43 citations*
22. **[Memory-based Parameter Adaptation ↗](https://arxiv.org/abs/1802.10542) arXiv (Cornell University) · no summary yet**Pablo Sprechmann et al.*2018 · 42 citations*
23. **[Pointer Graph Networks ↗](https://arxiv.org/abs/2006.06380) arXiv:2006.06380 · no summary yet**Petar Veličković et al.*2020 · 25 citations*
24. **[RecurrentGemma: Moving Past Transformers for Efficient Open Language Models ↗](https://arxiv.org/abs/2404.07839) arXiv (Cornell University) · no summary yet**Aleksandar Botev et al.*2024 · 22 citations*
25. **[Learned-norm pooling for deep neural networks. ↗](https://arxiv.org/abs/1311.1780) arXiv (Cornell University) · no summary yet**Çağlar Gülçehre et al.*2013 · 6 citations*

[See all 27 works by Razvan Pascanu →](https://md.research.elamur.ai/free/en/authors/razvan-pascanu/works/)

## Co-authors here

12 of 19 co-authors with a page, the most papers together first.

- [Caglar Gulcehre](https://md.research.elamur.ai/free/en/authors/caglar-gulcehre/) ×2
- [Yoshua Bengio](https://md.research.elamur.ai/free/en/authors/yoshua-bengio/) ×2
- [Adam Santoro](https://md.research.elamur.ai/free/en/authors/adam-santoro/)
- [Albert Gu](https://md.research.elamur.ai/free/en/authors/albert-gu/)
- [Antonio Orvieto](https://md.research.elamur.ai/free/en/authors/antonio-orvieto/)
- [David G. T. Barrett](https://md.research.elamur.ai/free/en/authors/david-g-t-barrett/)
- [David Raposo](https://md.research.elamur.ai/free/en/authors/david-raposo/)
- [David Warde-Farley](https://md.research.elamur.ai/free/en/authors/david-warde-farley/)
- [Frédéric Bastien](https://md.research.elamur.ai/free/en/authors/frederic-bastien/)
- [Ian Goodfellow](https://md.research.elamur.ai/free/en/authors/ian-goodfellow/)
- [Jelena Luketina](https://md.research.elamur.ai/free/en/authors/jelena-luketina/)
- [Jonathan Schwarz](https://md.research.elamur.ai/free/en/authors/jonathan-schwarz/)

## Venues

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

- International Conference on Learning Representations
- Lecture notes in computer science

## Cited by

Papers of our library cite their works 1,344 times (of the 149,439 papers whose bibliographies we read); [153 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/razvan-pascanu/cited-by/).

Updated 2 November 2026