Reward-Aligned Reweighting for On-Policy Distillation
cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Project page: https://maa.org
Terminology
Sources
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
- Distilling the Knowledge in a Neural Network
- Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe
- Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level
- Entropy-Aware On-Policy Distillation of Language Models
- Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
- Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation
- Outcome-Confounded Local Supervision in On-Policy Distillation
- KL for a KL: On-Policy Distillation with Control Variate Baseline
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- A Survey of On-Policy Distillation for Large Language Models
- Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation
- MiMo-V2-Flash Technical Report
- Trust Region On-Policy Distillation
- SG-OPD: Sign-Gated On-Policy Distillation via Sign-Consistency Gating and Phased Teacher Sampling
- KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning
- TIP: Token Importance in On-Policy Distillation
- Qwen3 Technical Report
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks