PreSO: Privileged Representation Isolation for On-Policy Self-Distillation
cs.LG, cs.AI
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- HealthBench: Evaluating Large Language Models Towards Improved Human Health
- Aligning Language Models from User Interactions
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs
- Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
- Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning
- Reinforcement Learning via Self-Distillation
- Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
- PHF: Privileged Hidden Flow for On-Policy Self-Distillation
- When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning
- Self-Distilled Agentic Reinforcement Learning
- RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Purified OPSD: On-Policy Self-Distillation Without Losing How to Think
- Qwen3 Technical Report
- Contrastive Representation Distillation
- Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
- STEPS: Selective On-Policy Self-Distillation for Reasoning
- Learning to Reason under Off-Policy Guidance
- Self-Distilled RLVR
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