Elamur Research⌕
☰
home / authors / Arthur D. Szlam

Arthur D. Szlam

Arthur D. Szlam has 4 papers in our library, in 2018–2022, most of them on Dialogue systems, Language models & pretraining, Reasoning; often with Jason Weston, Douwe Kiela, Emily Dinan.

4 papers in our library · 2018–2022

OpenAlex · h-index 45 · 139 works · 15,716 citations OpenAlex, 2026-10-14

📄 4 works in our library · 🔗 Cited 1,873 times in our library · 20 more in our library without a page yet · ⭐ Paper Stars ranking: #1098

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🏢MetaMenlo Park · United States2014–2023 · 45 papers🎓City College of New YorkNew York · United States2011–2021 · 13 papers🏢MetaTel Aviv · Israel2015–2021 · 8 papers🎓University of California, Los AngelesLos Angeles · United States2008–2009 · 8 papers🎓New York UniversityNew York · United States2010–2013 · 6 papers🎓Courant Institute of Mathematical SciencesNew York · United States2010–2013 · 5 papers🎓Yale UniversityNew Haven · United States2005–2006 · 5 papers🎓City University of New YorkNew York · United States2012–2014 · 4 papers🏢MetaLondon · United Kingdom2020–2022 · 3 papers🎓Georgia Institute of TechnologyAtlanta · United States2021–2023 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 6 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 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 4 worksComputer Science · 4 worksArtificial Intelligence · 4 worksLanguage and Linguistics · 4 worksInformation Systems · 1 work

🧭 Topics 3Research subjects and languages the work is about.Dialogue systems · 4 worksReasoning · 1 workLanguage models & pretraining · 1 work

💡 Concepts 1Key ideas and methods explained on our concept pages.Inverted index · 1 work

 Works by year

2020s

20221 paper

2010s

20192 papers20181 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Personalizing Dialogue Agents: I have a dog, do you have pets too? (2018 · 1,854 citations)
    Open-domain chit-chat models tend to give vague answers, lack a stable personality and are rarely engaging.
  2. The Second Conversational Intelligence Challenge (ConvAI2) (2019 · 530 citations)
    ConvAI2 was a NeurIPS 2018 competition meant to give open-domain chit-chat systems a shared benchmark and a clear evaluation protocol.
  3. Dialogue Natural Language Inference (2019 · 385 citations)
    Chit-chat agents often produce replies that clash with their earlier turns or with their assigned persona, for example by claiming two different jobs.
  4. Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion (2022 · 132 citations)
    Large language models often produce fluent but false statements, and their knowledge stops at the training date. This paper presents SeeKeR (Search-engine→Knowledge→Response), which extends the earlier K2R approach with internet search. One transformer runs three steps in sequence, each marked by special tokens:

All works

24 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

  1. Spectral Networks and Locally Connected Networks on Graphs ↗arXiv (Cornell University) · no summary yetJoan Bruna et al.2013 · 2,651 citations
  2. Personalizing Dialogue Agents: I have a dog, do you have pets too?Annual Meeting of the Association for Computational Linguistics (ACL)Saizheng Zhang, Emily Dinan, Jack Urbanek, et al.2018 · 1,854 citations
  3. Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks ↗arXiv (Cornell University) · no summary yetEmily Denton et al.2015 · 1,626 citations
  4. The Second Conversational Intelligence Challenge (ConvAI2)arXiv:1902.00098Emily Dinan, Varvara Logacheva, Valentin Malykh, et al.2019 · 530 citations
  5. Dialogue Natural Language InferenceAnnual Meeting of the Association for Computational Linguistics (ACL)Sean Welleck, Jason Weston, Arthur Szlam, et al.2019 · 385 citations
  6. Beyond Goldfish Memory: Long-Term Open-Domain Conversation ↗Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetJing Xu, Arthur Szlam, Jason Weston2022 · 275 citations
  7. Learning to Speak and Act in a Fantasy Text Adventure Game ↗arXiv:1903.03094 · no summary yetJack Urbanek et al.2019 · 243 citations
  8. Tracking the World State with Recurrent Entity Networks ↗arXiv:1612.03969 · ICLR 2017 · no summary yetMikael Henaff et al.2016 · 228 citations
  9. Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt CompletionFindings of the Association for Computational LinguisticsKurt Shuster, Mojtaba Komeili, Leonard Adolphs, et al.2022 · 132 citations
  10. Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems ↗arXiv:1511.06931 · no summary yetJesse Dodge et al.2015 · 111 citations
  11. CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory ↗arXiv:2210.05663 · no summary yetNur Muhammad Mahi Shafiullah et al.2023 · 93 citations
  12. A Mathematical Motivation for Complex-Valued Convolutional Networks ↗Neural Computation · no summary yetMark Tygert et al.2016 · 87 citations
  13. Hard Mixtures of Experts for Large Scale Weakly Supervised Vision ↗arXiv:1704.06363 · no summary yetSam Gross, Marc'Aurelio Ranzato, Arthur Szlam2017 · 85 citations
  14. Transformation-Based Models of Video Sequences ↗arXiv (Cornell University) · no summary yetJoost van Amersfoort et al.2017 · 60 citations
  15. Unsupervised Feature Learning by Deep Sparse Coding ↗SIAM International Conference on Data Mining · no summary yetYunlong He et al.2014 · 59 citations
  16. MazeBase: A Sandbox for Learning from Games ↗arXiv (Cornell University) · no summary yetSainbayar Sukhbaatar et al.2015 · 49 citations
  17. Convolutional Matching Pursuit and Dictionary Training ↗arXiv (Cornell University) · no summary yetArthur D. Szlam, Koray Kavukcuoglu, Yann LeCun2010 · 27 citations
  18. Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent ↗arXiv (Cornell University) · no summary yetZhilin Yang et al.2017 · 17 citations
  19. Order-Aware Generative Modeling Using the 3D-Craft Dataset ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetZhuoyuan Chen et al.2019 · 12 citations
  20. Scale-invariant learning and convolutional networks ↗Applied and Computational Harmonic Analysis · no summary yetSoumith Chintala et al.2016 · 10 citations
  21. Training Language Models Using Target-Propagation ↗arXiv (Cornell University) · no summary yetSam Wiseman et al.2017 · 8 citations
  22. A theoretical argument for complex-valued convolutional networks ↗arXiv (Cornell University) · no summary yetJoan Bruna et al.2015 · 3 citations
  23. droidlet: modular, heterogenous, multi-modal agents ↗Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · no summary yetAnurag Pratik et al.2021 · 1 citation
  24. Decoupled DiLoCo for Resilient Distributed Pre-training ↗arXiv (Cornell University) · no summary yetArthur Douillard et al.2026

 Co-authors here

12 of 17 co-authors with a page, the most papers together first.

Venues

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

 Cited by

Papers of our library cite their works 1,873 times (of the 149,439 papers whose bibliographies we read); 233 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/arthur-d-szlam/