Alexey Gorbatovski

Alexey Gorbatovski on Hugging Face Daily Papers: 5 papers, 5 in the top 3 of their day, 427 upvotes.

1. Trust-Region Behavior Blending for On-Policy Distillation 65 upvotes, #3 of 2026-06-01
2. F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare 70 upvotes, #1 of 2026-02-09
3. The Differences Between Direct Alignment Algorithms are a Blur 109 upvotes, #2 of 2025-02-04
4. Learn Your Reference Model for Real Good Alignment 75 upvotes, #1 of 2024-04-16
5. Linear Transformers with Learnable Kernel Functions are Better In-Context Models 81 upvotes, #1 of 2024-02-19

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.