Alexey Malakhov
Identifiers
- name variant Alexey Malakhov 0.60 · backfill
Papers (3)
- Trust-Region Behavior Blending for On-Policy Distillation cs.LG · 2026 · author #3
- F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare cs.LG · 2026 · author #5
- The Differences Between Direct Alignment Algorithms are a Blur cs.LG · 2025 · author #4
Mentions
- 2605.31159 #3 · arxiv_oai · confidence 0.70 Alexey Malakhov
- 2602.06717 #5 · arxiv_oai · confidence 0.70 Alexey Malakhov
Frequent Coauthors
- Alexey Gorbatovski 3 shared papers
- Boris Shaposhnikov 3 shared papers
- Daniil Gavrilov 3 shared papers
- Daniil Plyusov 2 shared papers
- Daria Korotyshova 2 shared papers
- Viacheslav Sinii 2 shared papers
- Nikita Balagansky 1 shared papers