Explorer

• .. (Parent Directory)
• 2604.00626 - A Survey of On-Policy Distillation for Large Language Models.pdf
• 2604.00860 - Policy Improvement Reinforcement Learning.pdf
• 2604.02509 - Rapidly deploying on-device eye tracking by distilling visual foundation models.pdf
• 2604.12002 - Self-Distillation Zero - Self-Revision Turns Binary Rewards into Dense Supervision.pdf
• 2604.14084 - TIP - Token Importance in On-Policy Distillation.pdf
• 2604.23336 - Efficient Rationale-based Retrieval - On-policy Distillation from Generative Rerankers based on JEPA.pdf
• 2604.26940 - Select to Think - Unlocking SLM Potential with Local Sufficiency.pdf
• 2605.04062 - EdgeRazor - A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation.pdf