---
title: "Arthur D. Szlam — author profile and papers · Dialogue systems"
description: "Arthur D. Szlam: 7 papers on Elamur Research (2015–2022), h-index 45 — affiliations, topics, co-authors and who cites them in our library."
canonical: "https://research.elamur.ai/free/en/authors/arthur-d-szlam/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/arthur-d-szlam/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Arthur D. Szlam

# Arthur D. Szlam

Arthur D. Szlam has 7 papers in our library, in 2015–2022, most of them on [Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/), [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/); often with [Jason Weston](https://md.research.elamur.ai/free/en/authors/jason-weston/), [Douwe Kiela](https://md.research.elamur.ai/free/en/authors/douwe-kiela/), [Emily Dinan](https://md.research.elamur.ai/free/en/authors/emily-dinan/).

7 papers in our library · 2015–2022

[OpenAlex](https://openalex.org/A5053145694) · [**h-index 45**](https://openalex.org/authors/A5053145694) · [139 works](https://openalex.org/works?filter=author.id:A5053145694) · [15,716 citations](https://openalex.org/works?filter=author.id:A5053145694&sort=cited_by_count:desc) OpenAlex, 2026-10-14

[📄 7 works in our library](https://md.research.elamur.ai/free/en/authors/arthur-d-szlam/#papers) · [🔗 Cited 1,873 times in our library](https://md.research.elamur.ai/free/en/authors/arthur-d-szlam/cited-by/) · [17 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #1006](https://md.research.elamur.ai/free/en/paper-stars/page/11/#star-1006)

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

## Affiliations

[🏢**Meta** Menlo Park · United States 2014–2023 · 45 papers](https://md.research.elamur.ai/free/en/companies/meta/) · [🎓**City College of New York** New York · United States 2011–2021 · 13 papers](https://ror.org/00wmhkr98) · [🏢**Meta** Tel Aviv · Israel 2015–2021 · 8 papers](https://md.research.elamur.ai/free/en/companies/meta-israel/) · [🎓**University of California, Los Angeles** Los Angeles · United States 2008–2009 · 8 papers](https://md.research.elamur.ai/free/en/universities/university-of-california-los-angeles/) · [🎓**New York University** New York · United States 2010–2013 · 6 papers](https://md.research.elamur.ai/free/en/universities/new-york-university/) · [🎓**Courant Institute of Mathematical Sciences** New York · United States 2010–2013 · 5 papers](https://md.research.elamur.ai/free/en/universities/courant-institute-of-mathematical-sciences/) · [🎓**Yale University** New Haven · United States 2005–2006 · 5 papers](https://md.research.elamur.ai/free/en/universities/yale-university/) · [🎓**City University of New York** New York · United States 2012–2014 · 4 papers](https://md.research.elamur.ai/free/en/universities/city-university-of-new-york/) · [🏢**Meta** London · United Kingdom 2020–2022 · 3 papers](https://md.research.elamur.ai/free/en/companies/meta-united-kingdom/) · [🎓**Georgia Institute of Technology** Atlanta · United States 2021–2023 · 2 papers](https://md.research.elamur.ai/free/en/universities/georgia-institute-of-technology/)

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 6 The field of science this work belongs to (OpenAlex fields).[Arts and Humanities · 7 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Computer Science · 7 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 7 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Language and Linguistics · 7 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Computer Vision and Pattern Recognition · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Information Systems · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/)

🧭 Topics 4 Research subjects and languages the work is about.[Dialogue systems · 5 works](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · [Reasoning · 1 work](https://md.research.elamur.ai/free/en/topics/reasoning/) · [Language models & pretraining · 1 work](https://md.research.elamur.ai/free/en/topics/language-models/) · [Evaluation & benchmarks · 1 work](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/)

💡 Concepts 1 Key ideas and methods explained on our concept pages.[Inverted index · 1 work](https://md.research.elamur.ai/free/en/concepts/inverted-index/)

## Works by year

### 2020s

[**2022** 1 paper](https://md.research.elamur.ai/free/en/authors/arthur-d-szlam/year/2022/)

### 2010s

[**2019** 3 papers](https://md.research.elamur.ai/free/en/authors/arthur-d-szlam/year/2019/) · [**2018** 1 paper](https://md.research.elamur.ai/free/en/authors/arthur-d-szlam/year/2018/) · [**2016** 1 paper](https://md.research.elamur.ai/free/en/authors/arthur-d-szlam/year/2016/) · [**2015** 1 paper](https://md.research.elamur.ai/free/en/authors/arthur-d-szlam/year/2015/)

## Papers

The most cited first (OpenAlex and our library).

1. **[Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://md.research.elamur.ai/free/en/papers/zhang-2018-personalizing-dialogue-agents-i-have/)** *(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)](https://md.research.elamur.ai/free/en/papers/dinan-2019-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](https://md.research.elamur.ai/free/en/papers/welleck-2019-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. **[Learning to Speak and Act in a Fantasy Text Adventure Game](https://md.research.elamur.ai/free/en/papers/urbanek-2019-learning-speak-act-fantasy-text/)** *(2019 · 243 citations)* Most dialogue systems learn only from text and never connect words to a world they can perceive or change.
5. **[Tracking the World State with Recurrent Entity Networks](https://md.research.elamur.ai/free/en/papers/henaff-2016-tracking-world-state-recurrent-entity/)** *(2016 · 228 citations)* The paper addresses how a model can keep an up-to-date internal picture of a changing situation while it reads, such as the state of a short story, instead of reasoning only once a question arrives.
6. **[Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion](https://md.research.elamur.ai/free/en/papers/shuster-2022-language-models-that-seek-knowledge/)** *(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:
7. **[Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems](https://md.research.elamur.ai/free/en/papers/dodge-2015-evaluating-prerequisite-qualities-learning-end/)** *(2015 · 111 citations)* End-to-end neural dialog systems trained on raw human conversations are usually judged by BLEU, crowdsourcing or a few human ratings.

## All works

24 works of theirs in our library, the most cited first; 7 with a page here, the others link their original until we summarise them.

1. **[Spectral Networks and Locally Connected Networks on Graphs ↗](https://arxiv.org/abs/1312.6203) arXiv (Cornell University) · no summary yet**Joan Bruna et al.*2013 · 2,651 citations*
2. **[Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://md.research.elamur.ai/free/en/papers/zhang-2018-personalizing-dialogue-agents-i-have/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/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 ↗](https://arxiv.org/abs/1506.05751) arXiv (Cornell University) · no summary yet**Emily Denton et al.*2015 · 1,626 citations*
4. [**The Second Conversational Intelligence Challenge (ConvAI2) arXiv:1902.00098**Emily Dinan, Varvara Logacheva, Valentin Malykh, et al.*2019 · 530 citations*](https://md.research.elamur.ai/free/en/papers/dinan-2019-second-conversational-intelligence-challenge-convai2/)
5. **[Dialogue Natural Language Inference](https://md.research.elamur.ai/free/en/papers/welleck-2019-dialogue-natural-language-inference/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Sean Welleck, Jason Weston, Arthur Szlam, et al.*2019 · 385 citations*
6. **[Beyond Goldfish Memory: Long-Term Open-Domain Conversation ↗](https://aclanthology.org/2022.acl-long.356/) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Jing Xu, Arthur Szlam, Jason Weston*2022 · 275 citations*
7. [**Learning to Speak and Act in a Fantasy Text Adventure Game arXiv:1903.03094**Jack Urbanek, Angela Fan, Siddharth Karamcheti, et al.*2019 · 243 citations*](https://md.research.elamur.ai/free/en/papers/urbanek-2019-learning-speak-act-fantasy-text/)
8. **[Tracking the World State with Recurrent Entity Networks](https://md.research.elamur.ai/free/en/papers/henaff-2016-tracking-world-state-recurrent-entity/) [International Conference on Learning Representations (ICLR)](https://md.research.elamur.ai/free/en/venues/international-conference-on-learning-representations-iclr/)**Mikael Henaff, Jason Weston, Arthur Szlam, et al.*2016 · 228 citations*
9. **[Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion](https://md.research.elamur.ai/free/en/papers/shuster-2022-language-models-that-seek-knowledge/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Kurt Shuster, Mojtaba Komeili, Leonard Adolphs, et al.*2022 · 132 citations*
10. [**Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems arXiv:1511.06931**Jesse Dodge, Andreea Gane, Xiang Zhang, et al.*2015 · 111 citations*](https://md.research.elamur.ai/free/en/papers/dodge-2015-evaluating-prerequisite-qualities-learning-end/)
11. **[CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory ↗](https://doi.org/10.15607/rss.2023.xix.074) arXiv:2210.05663 · no summary yet**Nur Muhammad Mahi Shafiullah et al.*2023 · 93 citations*
12. **[A Mathematical Motivation for Complex-Valued Convolutional Networks ↗](https://doi.org/10.1162/neco_a_00824) Neural Computation · no summary yet**Mark Tygert et al.*2016 · 87 citations*
13. **[Hard Mixtures of Experts for Large Scale Weakly Supervised Vision ↗](https://arxiv.org/abs/1704.06363) arXiv:1704.06363 · no summary yet**Sam Gross, Marc'Aurelio Ranzato, Arthur Szlam*2017 · 85 citations*
14. **[Transformation-Based Models of Video Sequences ↗](https://arxiv.org/abs/1701.08435) arXiv (Cornell University) · no summary yet**Joost van Amersfoort et al.*2017 · 60 citations*
15. **[Unsupervised Feature Learning by Deep Sparse Coding ↗](https://doi.org/10.1137/1.9781611973440.103) SIAM International Conference on Data Mining · no summary yet**Yunlong He et al.*2014 · 59 citations*
16. **[MazeBase: A Sandbox for Learning from Games ↗](https://arxiv.org/abs/1511.07401) arXiv (Cornell University) · no summary yet**Sainbayar Sukhbaatar et al.*2015 · 49 citations*
17. **[Convolutional Matching Pursuit and Dictionary Training ↗](https://arxiv.org/abs/1010.0422) arXiv (Cornell University) · no summary yet**Arthur D. Szlam, Koray Kavukcuoglu, Yann LeCun*2010 · 27 citations*
18. **[Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent ↗](https://arxiv.org/abs/1711.07950) arXiv (Cornell University) · no summary yet**Zhilin Yang et al.*2017 · 17 citations*
19. **[Order-Aware Generative Modeling Using the 3D-Craft Dataset ↗](https://doi.org/10.1109/iccv.2019.00185) IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yet**Zhuoyuan Chen et al.*2019 · 12 citations*
20. **[Scale-invariant learning and convolutional networks ↗](https://doi.org/10.1016/j.acha.2016.06.005) Applied and Computational Harmonic Analysis · no summary yet**Soumith Chintala et al.*2016 · 10 citations*
21. **[Training Language Models Using Target-Propagation ↗](https://arxiv.org/abs/1702.04770) arXiv (Cornell University) · no summary yet**Sam Wiseman et al.*2017 · 8 citations*
22. **[A theoretical argument for complex-valued convolutional networks ↗](http://dblp.uni-trier.de/db/journals/corr/corr1503.html#BrunaCLPST15) arXiv (Cornell University) · no summary yet**Joan Bruna et al.*2015 · 3 citations*
23. **[droidlet: modular, heterogenous, multi-modal agents ↗](https://doi.org/10.1109/icra48506.2021.9561446) Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · no summary yet**Anurag Pratik et al.*2021 · 1 citation*
24. **[Decoupled DiLoCo for Resilient Distributed Pre-training ↗](https://arxiv.org/abs/2604.21428) arXiv (Cornell University) · no summary yet**Arthur Douillard et al.*2026*

## Co-authors here

12 of 28 co-authors with a page, the most papers together first.

- [Jason Weston](https://md.research.elamur.ai/free/en/authors/jason-weston/) ×6
- [Douwe Kiela](https://md.research.elamur.ai/free/en/authors/douwe-kiela/) ×3
- [Emily Dinan](https://md.research.elamur.ai/free/en/authors/emily-dinan/) ×3
- [Jack Urbanek](https://md.research.elamur.ai/free/en/authors/jack-urbanek/) ×3
- [Alexander Miller](https://md.research.elamur.ai/free/en/authors/alexander-miller/) ×2
- [Antoine Bordes](https://md.research.elamur.ai/free/en/authors/antoine-bordes/) ×2
- [Kurt Shuster](https://md.research.elamur.ai/free/en/authors/kurt-shuster/) ×2
- [Alan W Black](https://md.research.elamur.ai/free/en/authors/alan-w-black/)
- [Andreea Gane](https://md.research.elamur.ai/free/en/authors/andreea-gane/)
- [Angela Fan](https://md.research.elamur.ai/free/en/authors/angela-fan/)
- [Iulian Vlad Serban](https://md.research.elamur.ai/free/en/authors/iulian-vlad-serban/)
- [Jesse Dodge](https://md.research.elamur.ai/free/en/authors/jesse-dodge/)

## Venues

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

- [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/) ×3: [ACL 2019](https://md.research.elamur.ai/free/en/venues/acl/2019/), [ACL 2018](https://md.research.elamur.ai/free/en/venues/acl/2018/)
- [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/): [Findings of the Association for Computational Linguistics 2022](https://md.research.elamur.ai/free/en/venues/findings/2022/)
- [International Conference on Learning Representations (ICLR)](https://md.research.elamur.ai/free/en/venues/international-conference-on-learning-representations-iclr/): [ICLR 2016](https://md.research.elamur.ai/free/en/venues/international-conference-on-learning-representations-iclr/2016/)
- Applied and Computational Harmonic Analysis
- IEEE/CVF International Conference on Computer Vision (ICCV)
- Neural Computation
- Proceedings - IEEE International Conference on Robotics and Automation/Proceedings
- SIAM International Conference on Data Mining

## Cited by

Papers of our library cite their works 1,873 times (of the 149,439 papers whose bibliographies we read); [257 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/arthur-d-szlam/cited-by/).

Updated 2 November 2026