← Back to People
A research scientist at OpenAI who works on novel reinforcement learning algorithms for training general-purpose agents.
1
Mentions
1
Articles
1
Outlets
Associated Topics
Companies Covered
Coverage Patterns
How media typically covers Ekin Akyürek
Article Types
- research1
Media Angles
- technical1
Narrative Framing
- breakthrough1
Writes About
Articles
Most recent firstArticles Written
Ekin Akyürek as author
MIT paper shows LLMs can learn and fine-tune itself without human input
arXivresearchpositiveOct 14, 2025
MIT researchers introduced SEAL (Self-Adapting Language Models), a framework enabling LLMs to autonomously generate their own fine-tuning data and adapt their weights without human intervention through self-edits and reinforcement learning.
“Co-author of the paper on Self-Adapting Language Models”
LLMsAI ResearchFoundation ModelsReinforcement Learning