Elamur Research⌕
☰
home / authors / Lovish Madaan

Lovish Madaan

Lovish Madaan has 2 papers in our library, in 2025, most of them on Language models & pretraining, Evaluation & benchmarks; often with Amar Budhiraja, David Brandfonbrener, Deepak Nathani.

2 papers in our library · 2025

OpenAlex · h-index 3 · 15 works · 39 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 73 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #9135

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

🎓University College LondonLondon · United Kingdom2024–2025 · 8 paperscurrent🎓Ludwig-Maximilians-Universität MünchenMunich · Germany2024–2025 · 2 paperscurrent🏢GoogleMountain View · United States2021–2022 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 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 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 works

🧭 Topics 2Research subjects and languages the work is about.Evaluation & benchmarks · 1 workLanguage models & pretraining · 1 work

 Works by year

2020s

20252 papers

 Papers

The most cited first (OpenAlex and our library).

  1. MLGym: A New Framework and Benchmark for Advancing AI Research Agents (2025 · 50 citations)
    LLM agents are now used for software and ML engineering. Yet there has been no shared environment for testing how they handle open-ended AI research, and none that supports training them with learning algorithms. The authors introduce MLGym, a framework that exposes research tasks through a Gym interface. Agents work…
  2. The Art of Scaling Reinforcement Learning Compute for LLMs (2025 · 20 citations)
    Reinforcement learning now consumes a large share of LLM training compute. Unlike pre-training, though, it has no dependable way to forecast how a training recipe will behave as budgets grow. The authors tackle this with a study totalling over 400,000 GPU-hours on Nvidia GB200 hardware. Most runs use an 8B dense…

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. MLGym: A New Framework and Benchmark for Advancing AI Research AgentsarXiv:2502.14499Deepak Nathani, Lovish Madaan, Nicholas Roberts, et al.2025 · 50 citations
  2. The Art of Scaling Reinforcement Learning Compute for LLMsarXiv:2510.13786Devvrit Khatri, Lovish Madaan, Rishabh Tiwari, et al.2025 · 20 citations
  3. Rethinking Thinking Tokens: LLMs as Improvement Operators ↗arXiv (Cornell University) · no summary yetLovish Madaan et al.2025 · 8 citations

 Co-authors here

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

 Cited by

Papers of our library cite their works 73 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/lovish-madaan/