---
title: "Yilun Du — author profile and papers — Elamur Research"
description: "Yilun Du, Google: 5 papers on Elamur Research (2022–2026), h-index 16 — affiliations, topics, co-authors and who cites them in our library."
canonical: "https://research.elamur.ai/free/en/authors/yilun-du/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/yilun-du/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Yilun Du

# Yilun Du

Yilun Du has 5 papers in our library, in 2022–2026, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/); often with [Igor Mordatch](https://md.research.elamur.ai/free/en/authors/igor-mordatch/), [Joshua B. Tenenbaum](https://md.research.elamur.ai/free/en/authors/joshua-b-tenenbaum/), [Shuang Li](https://md.research.elamur.ai/free/en/authors/shuang-li/).

5 papers in our library · 2022–2026

[OpenAlex](https://openalex.org/A5041777043) · [ORCID](https://orcid.org/0000-0001-6792-5946) · [**h-index 16**](https://openalex.org/authors/A5041777043) · [73 works](https://openalex.org/works?filter=author.id:A5041777043) · [2,096 citations](https://openalex.org/works?filter=author.id:A5041777043&sort=cited_by_count:desc) OpenAlex, 2026-10-14

[📄 5 works in our library](https://md.research.elamur.ai/free/en/authors/yilun-du/#papers) · [🔗 Cited 1,031 times in our library](https://md.research.elamur.ai/free/en/authors/yilun-du/cited-by/) · [14 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #2760](https://md.research.elamur.ai/free/en/paper-stars/page/28/#star-2760)

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

## Affiliations

[🎓**Harvard University** Cambridge · United States 2024–2026 · 57 papers*current*](https://md.research.elamur.ai/free/en/universities/harvard-university/) · [🏢**Google** Mountain View · United States 2019–2026 · 6 papers*current*](https://md.research.elamur.ai/free/en/companies/google/) · [🎓**Massachusetts Institute of Technology** Cambridge · United States 2017–2026 · 69 papers](https://md.research.elamur.ai/free/en/universities/massachusetts-institute-of-technology/) · [🔬**MIT Computer Science and Artificial Intelligence Laboratory** Cambridge · United States 2018–2025 · 23 papers](https://md.research.elamur.ai/free/en/labs/mit-computer-science-and-artificial-intelligence-laboratory/) · [🏢**Google DeepMind** London · United Kingdom 2025 · 10 papers](https://md.research.elamur.ai/free/en/companies/google-deepmind/) · [🔬**Harvard University Press** Cambridge · United States 2026 · 3 papers](https://ror.org/006v7bf86)

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 8 The field of science this work belongs to (OpenAlex fields).[Computer Science · 5 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 5 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 2 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/) · [Engineering · 1 work](https://md.research.elamur.ai/free/en/shelves/engineering/) · [Computational Theory and Mathematics · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computational-theory-and-mathematics/) · [Control and Systems Engineering · 1 work](https://md.research.elamur.ai/free/en/shelves/engineering/control-and-systems-engineering/)

🧭 Topics 2 Research subjects and languages the work is about.[Language models & pretraining · 3 works](https://md.research.elamur.ai/free/en/topics/language-models/) · [Reasoning · 1 work](https://md.research.elamur.ai/free/en/topics/reasoning/)

## Works by year

### 2020s

[**2026** 1 paper](https://md.research.elamur.ai/free/en/authors/yilun-du/year/2026/) · [**2023** 3 papers](https://md.research.elamur.ai/free/en/authors/yilun-du/year/2023/) · [**2022** 1 paper](https://md.research.elamur.ai/free/en/authors/yilun-du/year/2022/)

## Papers

The most cited first (OpenAlex and our library).

1. **[Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://md.research.elamur.ai/free/en/papers/du-2023-improving-factuality-reasoning-language-models/)** *(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](https://md.research.elamur.ai/free/en/papers/chi-2023-diffusion-policy-visuomotor-policy-learning/)** *(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](https://md.research.elamur.ai/free/en/papers/li-2022-pre-trained-language-models-interactive/)** *(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](https://md.research.elamur.ai/free/en/papers/zhang-2023-building-cooperative-embodied-agents-modularly/)** *(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](https://md.research.elamur.ai/free/en/papers/zhao-2026-large-language-models-are-bad/)** *(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 Debate arXiv:2305.14325**Yilun Du, Shuang Li, Antonio Torralba, et al.*2023 · 587 citations*](https://md.research.elamur.ai/free/en/papers/du-2023-improving-factuality-reasoning-language-models/)
2. **[3D Shape Generation and Completion through Point-Voxel Diffusion ↗](https://doi.org/10.1109/iccv48922.2021.00577) IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yet**Linqi Zhou, Yilun Du, Jiajun Wu*2021 · 443 citations*
3. **[Kubric: A scalable dataset generator ↗](https://doi.org/10.1109/cvpr52688.2022.00373) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Klaus Greff et al.*2022 · 248 citations*
4. **[Neural Radiance Flow for 4D View Synthesis and Video Processing ↗](https://doi.org/10.1109/iccv48922.2021.01406) IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yet**Yilun Du et al.*2021 · 236 citations*
5. [**Diffusion Policy: Visuomotor Policy Learning via Action Diffusion arXiv:2303.04137**Cheng Chi, Zhenjia Xu, Siyuan Feng, et al.*2023 · 173 citations*](https://md.research.elamur.ai/free/en/papers/chi-2023-diffusion-policy-visuomotor-policy-learning/)
6. [**Pre-Trained Language Models for Interactive Decision-Making arXiv:2202.01771**Shuang Li, Xavier Puig, Chris Paxton, et al.*2022 · 124 citations*](https://md.research.elamur.ai/free/en/papers/li-2022-pre-trained-language-models-interactive/)
7. [**Building Cooperative Embodied Agents Modularly with Large Language Models arXiv:2307.02485**Hongxin Zhang, Weihua Du, Jiaming Shan, et al.*2023 · 95 citations*](https://md.research.elamur.ai/free/en/papers/zhang-2023-building-cooperative-embodied-agents-modularly/)
8. **[Foundation Models for Decision Making: Problems, Methods, and Opportunities ↗](https://arxiv.org/abs/2303.04129) arXiv:2303.04129 · no summary yet**Sherry Yang et al.*2023 · 92 citations*
9. **[Learning Interactive Real-World Simulators ↗](https://arxiv.org/abs/2310.06114) arXiv:2310.06114 · no summary yet**Sherry Yang et al.*2023 · 54 citations*
10. **[World Action Models are Zero-shot Policies ↗](https://arxiv.org/abs/2602.15922) arXiv (Cornell University) · no summary yet**Seonghyeon Ye et al.*2026 · 41 citations*
11. **[AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark ↗](https://arxiv.org/abs/2410.03051) arXiv (Cornell University) · no summary yet**Wenhao Chai et al.*2024 · 17 citations*
12. **[Looped Transformers for Length Generalization ↗](https://arxiv.org/abs/2409.15647) arXiv:2409.15647 · no summary yet**Ying Fan et al.*2024 · 13 citations*
13. **[Learning Iterative Reasoning through Energy Diffusion ↗](https://arxiv.org/abs/2406.11179) arXiv:2406.11179 · no summary yet**Yilun Du, Jiayuan Mao, Joshua B. Tenenbaum*2024 · 11 citations*
14. **[Generative Modeling via Drifting ↗](https://arxiv.org/abs/2602.04770) arXiv (Cornell University) · no summary yet**Deng, Mingyang et al.*2026 · 9 citations*
15. **[MoCo: A One-Stop Shop for Model Collaboration Research ↗](https://arxiv.org/abs/2601.21257) arXiv (Cornell University) · no summary yet**Shangbin Feng et al.*2026 · 3 citations*
16. **[Compositional Generative Inverse Design ↗](https://arxiv.org/abs/2401.13171) arXiv (Cornell University) · no summary yet**Tailin Wu et al.*2024 · 3 citations*
17. **[Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models ↗](https://arxiv.org/abs/2603.12248) arXiv (Cornell University) · no summary yet**Samy Jelassi et al.*2026 · 1 citation*
18. **[Large Language Models Are Bad Dice Players: LLMs Struggle to Generate Random Numbers from Statistical Distributions](https://md.research.elamur.ai/free/en/papers/zhao-2026-large-language-models-are-bad/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Minda Zhao, Yilun Du, Mengyu Wang*2026*
19. **[B-spline Policy: Accelerating Manipulation Policies via B-spline Action Representations ↗](https://arxiv.org/abs/2607.09648) arXiv (Cornell University) · no summary yet**Xiaoshen Han et al.*2026*

## Co-authors here

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

- [Igor Mordatch](https://md.research.elamur.ai/free/en/authors/igor-mordatch/) ×2
- [Joshua B. Tenenbaum](https://md.research.elamur.ai/free/en/authors/joshua-b-tenenbaum/) ×2
- [Shuang Li](https://md.research.elamur.ai/free/en/authors/shuang-li/) ×2
- [Anima Anandkumar](https://md.research.elamur.ai/free/en/authors/anima-anandkumar/)
- [Antonio B. Torralba](https://md.research.elamur.ai/free/en/authors/antonio-b-torralba/)
- [Chuang Gan](https://md.research.elamur.ai/free/en/authors/chuang-gan/)
- [De-An Huang](https://md.research.elamur.ai/free/en/authors/de-an-huang/)
- [Ekin Akyurek](https://md.research.elamur.ai/free/en/authors/ekin-akyurek/)
- [Hongxin Zhang](https://md.research.elamur.ai/free/en/authors/hongxin-zhang/)
- [Jacob Andreas](https://md.research.elamur.ai/free/en/authors/jacob-andreas/)
- [Linxi Fan](https://md.research.elamur.ai/free/en/authors/linxi-fan/)
- [Mengyu Wang](https://md.research.elamur.ai/free/en/authors/mengyu-wang/)

## Venues

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

- IEEE/CVF International Conference on Computer Vision (ICCV) ×2
- [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/): [ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

## 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 →](https://md.research.elamur.ai/free/en/authors/yilun-du/cited-by/).

Updated 2 November 2026