CEPO sharpens token credit in RLVR by requiring tokens to be favored by the correct answer and disfavored by wrong answers drawn from rejected rollouts, delivering accuracy gains on five multimodal math benchmarks.
Hdpo: Hybrid distillation policy optimization via privileged self-distillation
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 9roles
background 3polarities
background 3representative citing papers
PBSD derives a reward-reweighted teacher distribution as the analytic optimum of a reward-regularized objective, yielding better stability and performance than KL-based self-distillation on math reasoning and tool-use tasks.
On-policy distillation works when student and teacher models share thinking patterns and the teacher adds new capabilities, with success tied to alignment on a small set of high-probability tokens.
GenEvolve introduces a self-evolving agent framework for image generation using tool-orchestrated trajectories and Visual Experience Distillation to achieve claimed SOTA results on benchmarks.
BRTS improves on-policy distillation by sampling multiple teacher rollouts and selecting the best one via a correctness-first then alignment priority rule, yielding gains on AIME and AMC math benchmarks.
This overview paper explains the conceptual foundations and design principles of On-Policy Self-Distillation for large language models from a beginner's perspective.
citing papers explorer
-
GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation
GenEvolve introduces a self-evolving agent framework for image generation using tool-orchestrated trajectories and Visual Experience Distillation to achieve claimed SOTA results on benchmarks.
-
On-Policy Distillation with Best-of-N Teacher Rollout Selection
BRTS improves on-policy distillation by sampling multiple teacher rollouts and selecting the best one via a correctness-first then alignment priority rule, yielding gains on AIME and AMC math benchmarks.