Elamur Research⌕
☰
home / authors / Yilun Du

Yilun Du

Yilun Du has 5 papers in our library, in 2022–2026, most of them on Language models & pretraining, Reasoning; often with Igor Mordatch, Joshua B. Tenenbaum, Shuang Li.

5 papers in our library · 2022–2026

OpenAlex · ORCID · h-index 16 · 73 works · 2,096 citations OpenAlex, 2026-10-14

📄 5 works in our library · 🔗 Cited 1,031 times in our library · 14 more in our library without a page yet · ⭐ Paper Stars ranking: #2760

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

🎓Harvard UniversityCambridge · United States2024–2026 · 57 paperscurrent🏢GoogleMountain View · United States2019–2026 · 6 paperscurrent🎓Massachusetts Institute of TechnologyCambridge · United States2017–2026 · 69 papers🔬MIT Computer Science and Artificial Intelligence LaboratoryCambridge · United States2018–2025 · 23 papers🏢Google DeepMindLondon · United Kingdom2025 · 10 papers🔬Harvard University PressCambridge · United States2026 · 3 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 8The field of science this work belongs to (OpenAlex fields).Computer Science · 5 worksArtificial Intelligence · 5 worksArts and Humanities · 2 worksLanguage and Linguistics · 2 worksComputer Vision and Pattern Recognition · 1 workEngineering · 1 workComputational Theory and Mathematics · 1 workControl and Systems Engineering · 1 work

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 3 worksReasoning · 1 work

 Works by year

2020s

20261 paper20233 papers20221 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Improving Factuality and Reasoning in Language Models through Multiagent Debate (2023 · 587 citations)
    LLMs often state invented facts with confidence or make unjustified leaps in multi-step reasoning. Earlier fixes such as chain-of-thought, self-verification and reflection all work inside a single model instance. This paper instead runs several copies of a language model as separate "agents." Each agent first answers…
  2. Diffusion Policy: Visuomotor Policy Learning via Action Diffusion (2023 · 173 citations)
    Learning robot control from human demonstrations can be framed as supervised regression, but robot actions are hard targets.
  3. Pre-Trained Language Models for Interactive Decision-Making (2022 · 124 citations)
    The paper asks whether language models trained only on text can serve as a backbone for sequential decision-making, even when the task involves no language.
  4. Building Cooperative Embodied Agents Modularly with Large Language Models (2023 · 95 citations)
    The paper studies teamwork between embodied agents that each act alone, see only partial raw sensory input, pay a time cost for every message, and share long-horizon household tasks with several sub-goals.
  5. Large Language Models Are Bad Dice Players: LLMs Struggle to Generate Random Numbers from Statistical Distributions (2026)
    LLMs are increasingly used inside pipelines that need genuinely random output, such as synthetic data, simulations and test construction.

All works

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

  1. Improving Factuality and Reasoning in Language Models through Multiagent DebatearXiv:2305.14325Yilun Du, Shuang Li, Antonio Torralba, et al.2023 · 587 citations
  2. 3D Shape Generation and Completion through Point-Voxel Diffusion ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetLinqi Zhou, Yilun Du, Jiajun Wu2021 · 443 citations
  3. Kubric: A scalable dataset generator ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetKlaus Greff et al.2022 · 248 citations
  4. Neural Radiance Flow for 4D View Synthesis and Video Processing ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetYilun Du et al.2021 · 236 citations
  5. Diffusion Policy: Visuomotor Policy Learning via Action DiffusionarXiv:2303.04137Cheng Chi, Zhenjia Xu, Siyuan Feng, et al.2023 · 173 citations
  6. Pre-Trained Language Models for Interactive Decision-MakingarXiv:2202.01771Shuang Li, Xavier Puig, Chris Paxton, et al.2022 · 124 citations
  7. Building Cooperative Embodied Agents Modularly with Large Language ModelsarXiv:2307.02485Hongxin Zhang, Weihua Du, Jiaming Shan, et al.2023 · 95 citations
  8. Foundation Models for Decision Making: Problems, Methods, and Opportunities ↗arXiv:2303.04129 · no summary yetSherry Yang et al.2023 · 92 citations
  9. Learning Interactive Real-World Simulators ↗arXiv:2310.06114 · no summary yetSherry Yang et al.2023 · 54 citations
  10. World Action Models are Zero-shot Policies ↗arXiv (Cornell University) · no summary yetSeonghyeon Ye et al.2026 · 41 citations
  11. AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark ↗arXiv (Cornell University) · no summary yetWenhao Chai et al.2024 · 17 citations
  12. Looped Transformers for Length Generalization ↗arXiv:2409.15647 · no summary yetYing Fan et al.2024 · 13 citations
  13. Learning Iterative Reasoning through Energy Diffusion ↗arXiv:2406.11179 · no summary yetYilun Du, Jiayuan Mao, Joshua B. Tenenbaum2024 · 11 citations
  14. Generative Modeling via Drifting ↗arXiv (Cornell University) · no summary yetDeng, Mingyang et al.2026 · 9 citations
  15. MoCo: A One-Stop Shop for Model Collaboration Research ↗arXiv (Cornell University) · no summary yetShangbin Feng et al.2026 · 3 citations
  16. Compositional Generative Inverse Design ↗arXiv (Cornell University) · no summary yetTailin Wu et al.2024 · 3 citations
  17. Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models ↗arXiv (Cornell University) · no summary yetSamy Jelassi et al.2026 · 1 citation
  18. Large Language Models Are Bad Dice Players: LLMs Struggle to Generate Random Numbers from Statistical DistributionsAnnual Meeting of the Association for Computational Linguistics (ACL)Minda Zhao, Yilun Du, Mengyu Wang2026
  19. B-spline Policy: Accelerating Manipulation Policies via B-spline Action Representations ↗arXiv (Cornell University) · no summary yetXiaoshen Han 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 1,031 times (of the 149,439 papers whose bibliographies we read); 204 citing papers with a page here →.

Updated

↑ back to top

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