--- title: "Timothy Lillicrap — author profile and papers" description: "Timothy Lillicrap, Google DeepMind: 2 papers on Elamur Research (2017–2019), h-index 57 — affiliations, topics, co-authors and who cites them in our…" canonical: "https://research.elamur.ai/free/en/authors/timothy-lillicrap/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/timothy-lillicrap/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Timothy Lillicrap # Timothy Lillicrap Timothy Lillicrap works on neural network architectures for machine learning. The two papers here take up two related problems. One is how a network can answer questions that depend on relations between entities rather than on the entities alone. The other is how a sequence model can keep useful information over long spans without the cost of memory and attention growing out of hand. Both propose a component that can be added to existing models. The more cited of the two is [A simple neural network module for relational reasoning](https://md.research.elamur.ai/free/en/papers/santoro-2017-simple-neural-network-module-relational/) (2017), which introduced the Relation Network. A single shared function is applied to every pair of input objects, the pairwise outputs are summed, and a second network processes the total. This makes the module insensitive to object order and lets it learn one relation function for all pairs. The objects can be cells of an image feature map, encoded sentences, or rows of a state description. The later paper, [Compressive Transformers for Long-Range Sequence Modelling](https://md.research.elamur.ai/free/en/papers/rae-2019-compressive-transformers-long-range-sequence/) (2019), moves toward language modelling over long histories. Instead of discarding old activations once a fixed-size buffer fills, the model folds them into a second, coarser compressed memory, for instance by merging several slots with a strided convolution. Attention then reads from both memories. The compression step has a training objective of its own, which measures how closely attention on the condensed slots matches attention on the full, uncompressed ones. Lillicrap is based at [Google DeepMind](https://md.research.elamur.ai/free/en/companies/google-deepmind/) in London, with earlier bylines at [Google](https://md.research.elamur.ai/free/en/companies/google-united-kingdom/) in Mountain View, [University College London](https://md.research.elamur.ai/free/en/universities/university-college-london/) and the [University of Oxford](https://md.research.elamur.ai/free/en/universities/university-of-oxford/), and education at [Queen's University](https://md.research.elamur.ai/free/en/universities/queen-s-university/) in Kingston, Canada, until 2014. Co-authors on the papers here include [Adam Santoro](https://md.research.elamur.ai/free/en/authors/adam-santoro/), [Peter Battaglia](https://md.research.elamur.ai/free/en/authors/peter-battaglia/), [David Raposo](https://md.research.elamur.ai/free/en/authors/david-raposo/), [Mateusz Malinowski](https://md.research.elamur.ai/free/en/authors/mateusz-malinowski/) and [Anna Potapenko](https://md.research.elamur.ai/free/en/authors/anna-potapenko/). The work is listed under [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/). Timothy Lillicrap has 2 papers in our library, in 2017–2019, most of them on [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/); often with [Adam Santoro](https://md.research.elamur.ai/free/en/authors/adam-santoro/), [Anna Potapenko](https://md.research.elamur.ai/free/en/authors/anna-potapenko/), [David Raposo](https://md.research.elamur.ai/free/en/authors/david-raposo/). 2 papers in our library · 2017–2019 [OpenAlex](https://openalex.org/A5066294254) · [ORCID](https://orcid.org/0000-0001-8918-486X) · [Wikidata](https://www.wikidata.org/wiki/Q51035916) · [**h-index 57**](https://openalex.org/authors/A5066294254) · [142 works](https://openalex.org/works?filter=author.id:A5066294254) · [62,840 citations](https://openalex.org/works?filter=author.id:A5066294254&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/timothy-lillicrap/#papers) · [🔗 3,990 citations in our library](https://md.research.elamur.ai/free/en/authors/timothy-lillicrap/cited-by/) · [5 more in our library without a page yet](#also) · [⭐ Paper Star rank #2115](https://md.research.elamur.ai/free/en/paper-stars/page/22/#star-2115) 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=Timothy+Lillicrap) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Timothy+Lillicrap) · [dblp](https://dblp.org/search?q=Timothy+Lillicrap) · [ACL Anthology](https://aclanthology.org/search/?q=Timothy+Lillicrap) ## Affiliations [🏢**Google DeepMind** London · United Kingdom 2015–2026 · 52 papersEmployment*current*](https://md.research.elamur.ai/free/en/companies/google-deepmind/) · [🏢**Google** London · United Kingdom 2016–2026 · 3 papers*current*](https://md.research.elamur.ai/free/en/companies/google-united-kingdom/) · [🏢**Google** Mountain View · United States 2015–2024 · 28 papers](https://md.research.elamur.ai/free/en/companies/google/) · [🎓**University College London** London · United Kingdom 2018–2024 · 16 papersEmployment](https://md.research.elamur.ai/free/en/universities/university-college-london/) · [🎓**Queen's University** Kingston · Canada 2001–2014 · 9 papersEducation until 2014](https://md.research.elamur.ai/free/en/universities/queen-s-university/) · [🎓**University of Oxford** Oxford · United Kingdom 2013–2020 · 7 papers](https://md.research.elamur.ai/free/en/universities/university-of-oxford/) · [🎓**National University of Singapore** Singapore · Singapore 2020 · 2 papers](https://md.research.elamur.ai/free/en/universities/national-university-of-singapore/) 🏛️**La Salle Secondary School** Kingston · [Canada](https://md.research.elamur.ai/free/en/countries/canada/) Education 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. ## Topics [Reasoning (1)](https://md.research.elamur.ai/free/en/topics/reasoning/) ## Works by year ### 2010s [**2019** 1 paper](https://md.research.elamur.ai/free/en/papers/rae-2019-compressive-transformers-long-range-sequence/) · [**2017** 1 paper](https://md.research.elamur.ai/free/en/papers/santoro-2017-simple-neural-network-module-relational/) ## Papers The most cited first (OpenAlex and our library). 1. **[A simple neural network module for relational reasoning](https://md.research.elamur.ai/free/en/papers/santoro-2017-simple-neural-network-module-relational/)** *(2017 · 590 citations)* Neural networks such as CNNs and MLPs often fail at questions that depend on how entities relate to each other, rather than on the properties of single entities. 2. **[Compressive Transformers for Long-Range Sequence Modelling](https://md.research.elamur.ai/free/en/papers/rae-2019-compressive-transformers-long-range-sequence/)** *(2019 · 320 citations)* Transformer language models keep detailed activations of past tokens, but storing and attending over long histories gets expensive. ## Also in our library 5 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 5 co-authors with a page, the most papers together first. - [Adam Santoro](https://md.research.elamur.ai/free/en/authors/adam-santoro/) - [Anna Potapenko](https://md.research.elamur.ai/free/en/authors/anna-potapenko/) - [David Raposo](https://md.research.elamur.ai/free/en/authors/david-raposo/) - [Mateusz Malinowski](https://md.research.elamur.ai/free/en/authors/mateusz-malinowski/) - [Peter Battaglia](https://md.research.elamur.ai/free/en/authors/peter-battaglia/) ## Cited by Papers of our library cite their works 3,990 times (of the 140,884 papers whose bibliographies we read); [221 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/timothy-lillicrap/cited-by/).