AI People Wiki

Builders & open source

Laurent Sartran

First author of Transformer Grammars at DeepMind and co-author of the SynJax library for JAX

Laurent Sartran is first author of Transformer Grammars (2022), a class of Transformer language models that compose representations of syntactic constituents recursively; the paper lists Sartran at DeepMind, and the code is published in the google-deepmind GitHub organization under the Apache-2.0 license. With Miloš Stanojević, Sartran co-authored SynJax, a JAX library of vectorized inference algorithms for structured distributions such as alignments, segmentations, and trees, also published by google-deepmind under Apache-2.0.12345

At a glance

Current role
None confirmed in the sources
Work listed
2
Sources cited
10
Profile reviewed

Research

Sartran's papers include work on machine translation: Sartran co-authored "Better Document-Level Machine Translation with Bayes' Rule" (2019, accepted by TACL) and "Enabling arbitrary translation objectives with Adaptive Tree Search" (2022). Sartran also co-authored "Rapid Task-Solving in Novel Environments" (2020), on agents that explore and solve tasks in unfamiliar settings.678

As first author of Transformer Grammars (TACL 2022), Sartran studied adding syntactic inductive biases to Transformer language models by composing representations of constituents recursively. Later co-authored work covers continuous diffusion for categorical data (2022) and fine-grained vision-and-language evaluation (ACL 2023).12910

Open-source work

Code for Transformer Grammars and for SynJax, a JAX library of vectorized inference for structured distributions such as alignments, segmentations and trees written with Miloš Stanojević, is published in the google-deepmind GitHub organization under the Apache-2.0 license.345

Work and contributions

  • Transformer Grammars Open-source code

    First author of Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale (TACL 2022). The google-deepmind repository describes the approach, cites the paper as Sartran et al., and is published under the Apache-2.0 license.123

  • SynJax Open-source code

    Co-author with Miloš Stanojević of SynJax: Structured Probability Distributions for JAX (2023); the google-deepmind repository cites the paper and is published under the Apache-2.0 license.45

Timeline

  1. Co-authored "Better Document-Level Machine Translation with Bayes' Rule", later accepted by TACL.6
  2. Co-authored "Rapid Task-Solving in Novel Environments".8
  3. Co-authored "Enabling arbitrary translation objectives with Adaptive Tree Search".7
  4. Released Transformer Grammars as first author, listed with DeepMind.12
  5. Co-authored "Continuous diffusion for categorical data".9
  6. Co-authored "Measuring Progress in Fine-grained Vision-and-Language Understanding" (ACL 2023).10
  7. Co-authored SynJax, a JAX library for structured probability distributions, with Miloš Stanojević.4

Documented roles

The sources do not confirm a current role; these are the roles they document.

  • Listed with DeepMind on the Transformer Grammars paper (2022), DeepMind2

Companies in their history

Suggest a correction or removal

Profiles cover public professional work only, and each statement cites a source. If something is out of date, missing or wrong, tell us and link a source. People can also ask for their profile to be corrected or removed.

References

10 sources · profile reviewed Oct 21, 2026 · data updated Oct 21, 2026

  1. Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale (arXiv 2203.00633)arXiv · Paper · published Mar 1, 2022 · accessed Oct 21, 2026
  2. Transformer Grammars — paper PDF (author affiliations: DeepMind, University of Oxford)arXiv · Paper · published Mar 1, 2022 · accessed Oct 21, 2026
  3. google-deepmind/transformer_grammars README and licenseGoogle DeepMind (GitHub repository) · Repository · accessed Oct 21, 2026
  4. SynJax: Structured Probability Distributions for JAX (arXiv 2308.03291)arXiv · Paper · published Aug 7, 2023 · accessed Oct 21, 2026
  5. google-deepmind/synjax README and licenseGoogle DeepMind (GitHub repository) · Repository · accessed Oct 21, 2026
  6. Better Document-Level Machine Translation with Bayes' Rule (arXiv 1910.00553)arXiv · Paper · published Oct 1, 2019 · accessed Oct 21, 2026
  7. Enabling arbitrary translation objectives with Adaptive Tree Search (arXiv 2202.11444)arXiv · Paper · published Feb 23, 2022 · accessed Oct 21, 2026
  8. Rapid Task-Solving in Novel Environments (arXiv 2006.03662)arXiv · Paper · published Jun 5, 2020 · accessed Oct 21, 2026
  9. Continuous diffusion for categorical data (arXiv 2211.15089)arXiv · Paper · published Nov 28, 2022 · accessed Oct 21, 2026
  10. Measuring Progress in Fine-grained Vision-and-Language Understanding (arXiv 2305.07558)arXiv · Paper · published May 12, 2023 · accessed Oct 21, 2026