Elamur Research⌕
☰
home / authors / Suhas Kotha

Suhas Kotha

Suhas Kotha has 2 papers in our library, in 2023–2024, most of them on Language models & pretraining; often with Aditi Raghunathan, Jacob Mitchell Springer, Daniel Fried.

2 papers in our library · 2023–2024

OpenAlex · h-index 3 · 11 works · 26 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 134 times in our library · 4 more in our library without a page yet · ⭐ Paper Stars ranking: #7602

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

🎓Stanford UniversityStanford · United States2026 · 2 paperscurrent🎓Carnegie Mellon UniversityPittsburgh · United States2022–2024 · 4 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 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksComputer Vision and Pattern Recognition · 1 work

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

 Works by year

2020s

20241 paper20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Repetition Improves Language Model Embeddings (2024 · 73 citations)
    Strong text embeddings are usually built on encoders with bidirectional attention. Recent work adapting autoregressive LMs for embeddings typically switches them to bidirectional attention and often adds extra training. This paper asks whether that change is really needed. The authors propose echo embeddings . The…
  2. Understanding Catastrophic Forgetting in Language Models via Implicit Inference (2023 · 45 citations)
    Fine-tuning large language models, such as instruction-tuning or RLHF, often reduces abilities the pretrained model had.

All works

6 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. Repetition Improves Language Model EmbeddingsarXiv:2402.15449Jacob Mitchell Springer, Suhas Kotha, Daniel Fried, et al.2024 · 73 citations
  2. Understanding Catastrophic Forgetting in Language Models via Implicit InferencearXiv:2309.10105Suhas Kotha, Jacob Mitchell Springer, Aditi Raghunathan2023 · 45 citations
  3. A Safe Harbor for AI Evaluation and Red Teaming ↗arXiv (Cornell University) · no summary yetShayne Longpre et al.2024 · 22 citations
  4. Pre-training under infinite compute ↗arXiv (Cornell University) · no summary yetKim, Konwoo et al.2025 · 7 citations
  5. Replaying pre-training data improves fine-tuning ↗arXiv (Cornell University) · no summary yetSuhas Kotha, Percy Liang2026 · 2 citations
  6. Data-efficient pre-training by scaling synthetic megadocs ↗arXiv (Cornell University) · no summary yetKonwoo Kim et al.2026 · 1 citation

 Co-authors here

4 co-authors with a page, the most papers together first.

 Cited by

Papers of our library cite their works 134 times (of the 149,439 papers whose bibliographies we read); 26 citing papers with a page here →.

Updated

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