pith. sign in

Daniil Gavrilov

Identifiers

  • name variant Daniil Gavrilov 0.60 · backfill

Papers (4)

  1. Trust-Region Behavior Blending for On-Policy Distillation cs.LG · 2026 · author #7
  2. F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare cs.LG · 2026 · author #7
  3. The Differences Between Direct Alignment Algorithms are a Blur cs.LG · 2025 · author #5
  4. Self-Attentive Model for Headline Generation cs.CL · 2019 · author #1

Mentions

  • 2605.31159 #7 · arxiv_oai · confidence 0.70 Daniil Gavrilov
  • 2602.06717 #7 · arxiv_oai · confidence 0.70 Daniil Gavrilov

Frequent Coauthors