Temporal scheduling of credit allocation criteria over RLVR training, using trajectory percentiles to target heterogeneous behaviors, yields more stable policy entropy and better reasoning benchmark results than static allocation.
Explain in your own words: Improving reasoning via token- selective dual knowledge distillation.arXiv preprint arXiv:2603.13260
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.LG 4years
2026 4representative citing papers
ADWIN adaptively selects training horizons in on-policy distillation via prefix alignment checks, cutting end-to-end cost by up to 4.1x while matching or exceeding full-rollout accuracy on math and code benchmarks.
Uni-OPD improves on-policy distillation via student-side data balancing for informative rollouts and teacher-side outcome-guided margin calibration that restores order consistency with rewards.
A two-axis taxonomy of student entropy and teacher-student divergence identifies informative tokens in on-policy distillation, allowing near-full performance with 10-50% of tokens.
citing papers explorer
-
Not only where, But when: Temporal Scheduling for RLVR
Temporal scheduling of credit allocation criteria over RLVR training, using trajectory percentiles to target heterogeneous behaviors, yields more stable policy entropy and better reasoning benchmark results than static allocation.
-
ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation
ADWIN adaptively selects training horizons in on-policy distillation via prefix alignment checks, cutting end-to-end cost by up to 4.1x while matching or exceeding full-rollout accuracy on math and code benchmarks.
-
Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe
Uni-OPD improves on-policy distillation via student-side data balancing for informative rollouts and teacher-side outcome-guided margin calibration that restores order consistency with rewards.
-
TIP: Token Importance in On-Policy Distillation
A two-axis taxonomy of student entropy and teacher-student divergence identifies informative tokens in on-policy distillation, allowing near-full performance with 10-50% of tokens.