Elamur Research⌕
☰
home / authors / Kevin Ellis

Kevin Ellis

Kevin Ellis has 3 papers in our library, in 2019–2024, most of them on Code & programming languages; often with Armando Solar-Lezama, Joshua B. Tenenbaum, Maxwell Nye.

3 papers in our library · 2019–2024

OpenAlex · ORCID · h-index 17 · 53 works · 1,047 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 76 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #7616

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

🎓Cornell UniversityIthaca · United States2021–2026 · 33 paperscurrent🎓Massachusetts Institute of TechnologyCambridge · United States2014–2022 · 14 papers

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

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 3 worksArtificial Intelligence · 2 worksComputer Science Applications · 1 workInformation Systems · 1 work

🧭 Topics 1Research subjects and languages the work is about.Code & programming languages · 1 work

 Works by year

2020s

20241 paper20201 paper

2010s

20191 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Write, Execute, Assess: Program Synthesis with a REPL (2019 · 86 citations)
    Program synthesis is difficult because a small syntactic edit can drastically change what a program does, and neural networks struggle to learn this mapping.
  2. WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment (2024 · 32 citations)
    The paper asks how an AI agent could learn how an unfamiliar environment works from only a few interactions, then reuse that knowledge for new goals.
  3. DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning (2020 · 22 citations)
    Program induction treats learning a task as finding a program that produces the desired behavior. It generalizes well from a few examples and yields knowledge humans can read. In practice, though, it has relied on hand-crafted domain-specific languages (DSLs) and search procedures tuned to them. DreamCoder learns…

All works

4 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

  1. Write, Execute, Assess: Program Synthesis with a REPLarXiv:1906.04604Kevin Ellis, Maxwell Nye, Yewen Pu, et al.2019 · 86 citations
  2. WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the EnvironmentConference on Neural Information Processing Systems (NeurIPS)Hao Tang, Darren Key, Kevin Ellis2024 · 32 citations
  3. DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learningarXiv:2006.08381Kevin Ellis, Catherine Wong, Maxwell Nye, et al.2020 · 22 citations
  4. Challenges and Paths Towards AI for Software Engineering ↗Qeios · no summary yetAlex Gu et al.2025 · 12 citations

 Co-authors here

8 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 76 times (of the 149,439 papers whose bibliographies we read); 25 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/kevin-ellis/