Explorer
- .. (Parent Directory)
- 2607.00485 - Efficient Multilingual Reasoning Transfer via Progressive Code-Switching.pdf
- 2607.00514.pdf
- 2607.00714 - Self-conditioned Flow Map Language Models via Fixed-point Flows.pdf
- 2607.00916 - Condensing Large-Scale Datasets Directly with Minimal Information Loss.pdf
- 2607.01170.pdf
- 2607.01208 - Distill to Detect - Exposing Stealth Biases in LLMs through Cartridge Distillation.pdf
- 2607.01590 - Hawk - Harnessing Hardware-Aware Knowledge for High-Performance NPU Kernel Generation.pdf
- 2607.01763 - Denser $neq$ Better - Limits of On-Policy Self-Distillation for Continual Post-Training.pdf
- 2607.01851 - Geometric Foundation Model Distillation for Efficient Lunar 3D Reconstruction.pdf
- 2607.01906 - SFKD - Spatial--Frequency Joint-Aware Heterogeneous Knowledge Distillation via Multi-Level Wavelet Spectral Interaction.pdf
- 2607.02234 - Purified OPSD - On-Policy Self-Distillation Without Losing How to Think.pdf
- 2607.02460 - Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation.pdf
- 2607.02502 - DemoPSD - Disagreement-Modulated Policy Self-Distillation.pdf
- 2607.02966 - Distill Where the Student Goes - Teacher-Regularized RL for English-Evidence Cross-Lingual RAG.pdf
- 2607.04428 - dOPSD - On-Policy Self-Distillation for Diffusion Language Models.pdf
- 2607.04763 - Multi-Turn On-Policy Distillation with Prefix Replay.pdf
- 2607.05184 - Rethinking On-Policy Self-Distillation for Thinking Models.pdf
- 2607.05394 - Weak-to-Strong Generalization via Direct On-Policy Distillation.pdf
- 2607.05804 - TurnOPD - Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training.pdf
- 2607.05891 - Few-Medoids - An Embarrassingly Simple Coreset Selection Method for Few-Shot Knowledge Distillation.pdf
- 2607.07050 - Behavior Leverage Imbalance in Multi-Teacher On-Policy Distillation.pdf
- 2607.07050 - Diagnosing and Calibrating Tool-Call Boundary Drift in Multi-Teacher On-Policy Distillation.pdf
- 2607.07820 - DeepSearch-World - Self-Distillation for Deep Search Agents in a Verifiable Environment.pdf
- 2607.08161 - SQuaD-SQL - Efficient Text-to-SQL with Small Language Models via LLM-Guided Knowledge Distillation.pdf
- 2607.08170 - Understanding Layer Patching in Model Size Interpolation.pdf
- 2607.08255 - Compete Then Collaborate - Frontier AI Teachers Build a Verifiable Curriculum to Improve a Coding Student Beyond Imitation.pdf
- 2607.08268 - Different Teachers, Different Capabilities - Sub-1B On-Device Distillation for Structured Text Enrichment.pdf
- 2607.08766 - OPSD-V - On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators.pdf
- 2607.10647 - Knowledge Distillation for Automated AI Tutor Evaluation.pdf
- 2607.10805 - Diagnosing and Mitigating Thinking Collapse in On-Policy Self-Distillation.pdf
- 2607.11012 - EasyOPD - An Easy-to-use On-Policy Distillation Framework for Large Language Models.pdf
- 2607.11257 - LaGuadia - Language-Guided Adaptive Distillation from Pathology Foundation Models.pdf
- 2607.11736 - MET - Theory-Grounded and Culture-Aware Multilingual Moral Reasoning.pdf
- 2607.12787 - Do We Really Need Multimodal Emotion Language Models Larger Than 1B Parameters.pdf
- 2607.13124 - ShortOPD - Recovering Pruned LLMs with Short-to-Long On-Policy Distillation.pdf
- 2607.13399 - Demystifying On-Policy Distillation - Roles, Pathologies, and Regulations.pdf
- 2607.13452 - Symbiosis-Inspired Knowledge Distillation for Incremental Object Detection.pdf
- 2607.13643 - Consensus as Privileged Context for Label-Free Self-Distillation.pdf
- 2607.14506 - Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards.pdf
- 2607.14552 - Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models.pdf
- 2607.14703 - Pretraining Multiple Instance Learning Networks with Multi-Teacher Distillation from Pathology Slide Foundation Models.pdf
- 2607.14709 - Gold-Guided Programmatic Distillation for Financial Reasoning over Hybrid Tables and Text.pdf
- 2607.14777 - SEED - Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning.pdf
- 2607.14947 - Optimal Self-Distillation for Rectified Flow via Linear Probing.pdf
- 2607.15161 - On-Policy Delta Distillation.pdf
- 2607.18042 - Anticipate Before Acting - Future-State-Conditioned Vision-Language Navigation.pdf
- 2607.20918 - OPOD - On-Policy Omni Distillation.pdf
- 2607.21361 - FedAgentKE - Federated Semantic Knowledge Evolution for Heterogeneous Agents.pdf
- 2607.21550 - X$^3$-OPD - Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment.pdf
- 2607.21556 - Visual Contrastive Self-Distillation.pdf