Ivan Medvedev

med1v's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers 11 days ago

VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training

Paper • 2602.10693 • Published 23 days ago • 216

Does Your Reasoning Model Implicitly Know When to Stop Thinking?

Paper • 2602.08354 • Published 26 days ago • 258

liked a Space 11 days ago

Running

Featured

57

QED-Nano: Teaching a Tiny Model to Prove Hard Theorems

📝

57

Who needs 1T parameters? Olympiad proofs with a 4B model