Despoina Magka
Despoina Magka has 2 papers in our library, in 2025, most of them on Evaluation & benchmarks, Language models & pretraining; often with Amar Budhiraja, Bingchen Zhao, Deepak Nathani.
OpenAlex · h-index 7 · 46 works · 206 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 50 times in our library · ⭐ Paper Stars ranking: #9590
Affiliations
Fields, topics and concepts
📚 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 worksInformation Systems · 1 work
🧭 Topics 2Research subjects and languages the work is about.Evaluation & benchmarks · 2 worksLanguage models & pretraining · 1 work
Works by year
2020s
Papers
- 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… - The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements (2025 · 4 citations)
The paper asks whether current AI research agents can reproduce known results in LLM training, which is a prerequisite for automating scientific research.
Co-authors here
- Amar Budhiraja
- Bingchen Zhao
- Deepak Nathani
- Dieuwke Hupkes
- Lovish Madaan
- Minqi Jiang
- Nikolay Bashlykov
- Roberta Raileanu
- Tatiana Shavrina
- Xian Li
Venues
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/despoina-magka/