🧑‍🔬 Rulin Shao

🏛️ Affiliations

🎓University of WashingtonSeattle · United States2023–2026 · 22 paperscurrent🎓Carnegie Mellon UniversityPittsburgh · United States2021–2026 · 7 paperscurrent🔬Allen Institute for Artificial IntelligenceSeattle · United States2025–2026 · 2 paperscurrent🎓Stanford UniversityStanford · United States2025–2026 · 2 paperscurrent🎓Princeton UniversityPrinceton · United States2026 · 1 papercurrent🎓University of California San DiegoSan Diego · United States2026 · 1 papercurrent🎓Xi'an Jiaotong UniversityXi'an · China2019–2020 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

🧭 Fields, topics and concepts

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

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs (2024 · 62 citations)
   Large language models often fail researchers who need to digest scientific literature. They invent references, rely on outdated pre-training knowledge, and seldom show the sources behind their claims. OpenScholar addresses this with a fully open retrieval-augmented system built on OpenScholar-DataStore (OSDS), an…
2. Spurious Rewards: Rethinking Training Signals in RLVR (2025 · 53 citations)
   Reinforcement learning with verifiable rewards (RLVR) is credited with improving math reasoning in language models, but it is unclear what in the training signal actually causes the gains.
3. Language models scale reliably with over-training and on downstream tasks (2024 · 46 citations)
   Scaling laws let teams forecast large language model behaviour from cheap small runs. Most published laws, however, assume Chinchilla-style compute-optimal training and predict only next-token loss. In practice, smaller models are often over-trained on far more tokens to cut inference cost, and they are compared on…
4. DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research (2025 · 28 citations)
   Open deep research (DR) agents are usually trained with reinforcement learning on short questions whose answers can be checked automatically. That kind of reward does not transfer to open-ended, long-form reports, where quality is loosely defined and checking claims requires current external evidence.

All works

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

1. OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMsarXiv:2411.14199Akari Asai, Jacqueline He, Rulin Shao, et al.2024 · 62 citations
2. Spurious Rewards: Rethinking Training Signals in RLVRarXiv:2506.10947Rulin Shao, Shuyue Stella Li, Rui Xin, et al.2025 · 53 citations
3. Language models scale reliably with over-training and on downstream tasksarXiv:2403.08540Samir Yitzhak Gadre, Georgios Smyrnis, Vaishaal Shankar, et al.2024 · 46 citations
4. Synthesizing scientific literature with retrieval-augmented language models ↗Nature · no summary yetAkari Asai et al.2026 · 42 citations
5. ReasonIR: Training Retrievers for Reasoning Tasks ↗arXiv (Cornell University) · no summary yetRulin Shao et al.2025 · 41 citations
6. DISTFLASHATTN: Distributed Memory-efficient Attention for Long-context LLMs Training ↗arXiv:2310.03294 · no summary yetDacheng Li et al.2023 · 36 citations
7. Scaling Retrieval-Based Language Models with a Trillion-Token Datastore ↗neural information processing systems · no summary yetRulin Shao et al.2024 · 30 citations
8. DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep ResearcharXiv:2511.19399Rulin Shao, Akari Asai, Shannon Zejiang Shen, et al.2025 · 28 citations
9. Cross-modal Attention Congruence Regularization for Vision-Language Relation Alignment ↗Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetRohan Pandey et al.2023 · 11 citations
10. Improving Factuality with Explicit Working Memory ↗Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetMingda Chen et al.2025 · 4 citations
11. JobBench: Aligning Agent Work With Human Will ↗arXiv (Cornell University) · no summary yetYuetai Li et al.2026 · 1 citation
12. ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research ↗arXiv (Cornell University) · no summary yetSohyeon Kim et al.2026
13. Context Language Models ↗arXiv (Cornell University) · no summary yetRulin Shao et al.2026
14. Efficient Test-Time Adaptation through Human-AI Interaction ↗arXiv (Cornell University) · no summary yetZora Zhiruo Wang et al.2026

🤝 Co-authors here

12 of 32 co-authors with a page, the most papers together first.

• Akari Asai ×2
• Rui Xin ×2
• Sewon Min ×2
• Alex Fang
• Amanpreet Singh
• David Sontag
• David Wadden
• Georgios Smyrnis
• Hamish Ivison
• Hannaneh Hajishirzi
• Jean Mercat
• Jeffrey Li

Venues

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

• Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) ×2
• Conference on Neural Information Processing Systems (NeurIPS)
• Nature
• neural information processing systems

🔗 Cited by

Papers of our library cite their works 590 times (of the 149,439 papers whose bibliographies we read); 147 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

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