Elamur Research⌕
☰
home / authors / Harm de Vries

Harm de Vries

Harm de Vries has 2 papers in our library, in 2017–2022, most of them on Question answering, Dialogue systems, Reasoning; often with Aaron Courville, Ethan Perez, Kaheer Suleman.

2 papers in our library · 2017–2022

OpenAlex · h-index 21 · 42 works · 5,894 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 578 times in our library · 3 more in our library without a page yet · ⭐ Paper Stars ranking: #3371

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

🏢ServiceNowSanta Clara · United States2021–2024 · 7 paperscurrent🎓University of Illinois Urbana-ChampaignUrbana · United States2024 · 1 papercurrent🎓Université de MontréalMontreal · Canada2015–2020 · 18 papers🔬Mila - Quebec Artificial Intelligence InstituteMontreal · Canada2017–2018 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksArtificial Intelligence · 2 worksComputer Vision and Pattern Recognition · 1 workArts and Humanities · 1 workInformation Systems · 1 workLanguage and Linguistics · 1 work

🧭 Topics 3Research subjects and languages the work is about.Reasoning · 1 workDialogue systems · 1 workQuestion answering · 1 work

 Works by year

2020s

20221 paperHarm de Vries's papers of 2022

2010s

20171 paperHarm de Vries's papers of 2017

 Papers

The most cited first (OpenAlex and our library).

  1. FiLM: Visual Reasoning with a General Conditioning Layer (2017 · 352 citations)
    Standard visual question answering models often fail on CLEVR, a benchmark of questions that need multi-step reasoning about rendered scenes.
  2. TopiOCQA: Open-domain Conversational Question Answering with Topic Switching (2022 · 143 citations)
    Benchmarks for conversational question answering (CQA), such as CoQA and QuAC, give the system a fixed reference passage and keep each dialogue on a single subject.

All works

5 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. FiLM: Visual Reasoning with a General Conditioning LayerarXiv:1709.07871Ethan Perez, Florian Strub, Harm de Vries, et al.2017 · 352 citations
  2. TopiOCQA: Open-domain Conversational Question Answering with Topic SwitchingTransactions of the Association for Computational Linguistics (TACL)Vaibhav Adlakha, Shehzaad Dhuliawala, Kaheer Suleman, et al.2022 · 143 citations
  3. Systematic Generalization: What Is Required and Can It Be Learned? ↗arXiv:1811.12889 · no summary yetDzmitry Bahdanau et al.2018 · 67 citations
  4. SelfCodeAlign: Self-Alignment for Code Generation ↗arXiv:2410.24198 · no summary yetYuxiang Wei et al.2024 · 30 citations
  5. Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models ↗arXiv:2401.00788 · no summary yetTerry Yue Zhuo et al.2024 · 20 citations

 Co-authors here

6 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 578 times (of the 141,840 papers whose bibliographies we read); 49 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/harm-de-vries/