🧑‍🔬 Jeffrey Li

🏛️ Affiliations

🏥Charité - Universitätsmedizin BerlinBerlin · Germany2025–2026 · 5 papersEmploymentcurrent🏥City Of Hope National Medical CenterDuarte · United States2024–2026 · 4 paperscurrent🔬German Centre for Cardiovascular ResearchBerlin · Germany2025–2026 · 4 paperscurrent🎓Humboldt-Universität zu BerlinBerlin · Germany2025–2026 · 4 paperscurrent🏥Deutsches Herzzentrum der CharitéBerlin · Germany2025–2026 · 3 paperscurrent🎓Carnegie Mellon UniversityPittsburgh · United States2025–2026 · 2 paperscurrent🎓Boston UniversityBoston · United States2026 · 1 papercurrent🎓Freie Universität BerlinBerlin · Germany2026 · 1 papercurrent🎓Georgia Institute of TechnologyAtlanta · United States2024 · 4 papers🎓University of WashingtonSeattle · United States2024–2025 · 3 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. DataComp-LM: In search of the next generation of training sets for language models (2024 · 191 citations)
   Pretraining datasets for language models are hard to compare fairly. Published models also differ in architecture, compute and hyperparameters, and the developers of top open-weight models seldom disclose their training data. DCLM (DataComp for Language Models) is a benchmark that fixes the training recipe so that…
2. 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…

All works

3 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. DataComp-LM: In search of the next generation of training sets for language modelsConference on Neural Information Processing Systems (NeurIPS)Jeffrey Li, Alex Fang, Georgios Smyrnis, et al.2024 · 191 citations
2. Language models scale reliably with over-training and on downstream tasksarXiv:2403.08540Samir Yitzhak Gadre, Georgios Smyrnis, Vaishaal Shankar, et al.2024 · 46 citations
3. Better Alignment with Instruction Back-and-Forth Translation ↗Findings of the Association for Computational Linguistics: EMNLP 2024 · no summary yetThao Nguyen et al.2024 · 10 citations

🤝 Co-authors here

12 of 15 co-authors with a page, the most papers together first.

• Alex Fang ×2
• Georgios Smyrnis ×2
• Rui Xin ×2
• Samir Yitzhak Gadre ×2
• Sedrick Keh ×2
• Etash Guha
• Hritik Bansal
• Jean Mercat
• Kushal Arora
• Maor Ivgi
• Marianna Nezhurina
• Mitchell Wortsman

Venues

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

• Conference on Neural Information Processing Systems (NeurIPS): NeurIPS 2024
• Findings of the Association for Computational Linguistics: EMNLP 2024

🔗 Cited by

Papers of our library cite their works 223 times (of the 149,439 papers whose bibliographies we read); 53 citing papers with a page here →.

Updated 30 October 2026

↑ back to top

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