Explorer
- .. (Parent Directory)
- 2610.00979 - RISED - RubrIcs for agentic multi-environment Selection and sElf-Distillation.pdf
- 2610.00997 - Distilling Directional Verification.pdf
- 2610.01435 - Distillation of Tabular Foundation Models into Efficient Predictors.pdf
- 2610.02117 - Where-OPD - Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes.pdf
- 2610.02179 - From Gradients to Capabilities - Understanding Multi-Teacher On-Policy Distillation.pdf
- 2610.02191 - The Missing Primitive - Diagnosing and Repairing Mathematical Reasoning in Large Language Models.pdf
- 2610.05048 - E$^2$-OPSD - Taming Entropy Overshoot in On-Policy Self-Distillation.pdf
- 2610.05200 - Learning without Overwriting - A Theory of Self-Distillation and Supervised Fine-Tuning in Continual Reasoning.pdf
- 2610.05303 - ASCENT - Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience.pdf
- 2610.05373 - Towards Unbiased On-Policy Distillation for Block Diffusion Language Models.pdf
- 2610.06342 - MeSD - Multi-Evidence Self-Distillation for VideoLLM.pdf
- 2610.06401 - RAISED - Self-Distillation for Robustness to Prompt Injection in LLM Agents.pdf
- 2610.07247 - Learning What to Distill - Bilevel Top-K Token Selection for Self-Distillation in Large Language Models.pdf
- 2610.07706 - WASD - Wasserstein-based Knowledge Distillation for Large Language Models.pdf
- 2610.07913 - Multimodal Knowledge Distillation for Gastric Adenocarcinoma Classification from Whole-Slide Images.pdf
- 2610.08077 - Self-Retrospection Distillation - Turning Post-hoc Experiences into Prior Foresight.pdf
- 2610.08448 - Rethinking Cross-Tokenizer On-Policy Distillation - From Alignment Coverage to Supervision Reliability.pdf
- 2610.09587 - Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curation.pdf
- 2610.09665 - SAPD - Step-Aligned Privileged Distillation.pdf
- 2610.10332 - Learning to Act with Task Progress - Distilling Small Agents from Compact Teacher Supervision.pdf
- 2610.10854 - KDFP - A first-principles approach to knowledge distillation in large language models.pdf
- 2610.11366 - SpatialOPSD - Self-Distilling Spatial Intelligence from Verified Coding Agent Traces.pdf
- 2610.11659 - DIAL-OPD - Learning More from Fewer Tokens in On-Policy Distillation.pdf
- 2610.11989 - MetaOPD - Meta-Learned Token Weighting for On-Policy Distillation.pdf
- 2610.12114 - Universal Textual Teaching for LLMs.pdf
- 2610.12137 - Poster - A Preliminary Study of LLM Distillation Inference.pdf
- 2610.12355 - Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models.pdf
- 2610.12367 - Which Skill to Distill SGUID - Selecting a Compact Skill Bank for Model-Skill Co-Evolution.pdf
- 2610.16354 - Self-Distillation with Verbal Regularization.pdf
- 2610.17593 - Training Generalist Navigation Policies via Action Self-Distillation.pdf
- 2610.17734 - Explore with Memory, Learn without It - In-Context Exploration and Self-Distillation for LLM Reasoning.pdf
- 2610.18162 - LoOPSD - On-Policy Self-Distillation with Looped Teachers.pdf
- 2610.18256 - Teach Me After You Learn It - Lookahead Self-Distillation for RLVR.pdf
- 2610.18517 - Imprinting - Knowledge Distillation Can Shift Student Behavior.pdf
- 2610.19601 - PA1-OPD - One-Step Prefix-Augmented On-Policy Distillation for Language Model Pretraining.pdf
- 2610.19687 - Function-Space Temporal Self-Distillation for Policy Optimization.pdf
- 2610.20516 - VASPO - Self-Distillation with Privileged Value Estimation.pdf
- 2610.22080 - Learning from Unverified Peers via Shared Residual Distillation.pdf
- 2610.23185 - A Stronger Teacher Within - Strengthening MoE Models via On-Policy Bidirectional Distillation.pdf
- 2610.25693 - ToolOPD - Credit-Aware On-Policy Distillation for Tool-Use Agents.pdf
- 2610.25880 - Asynchronous On-Policy Self-Distillation.pdf
- 2610.25973 - Correctness-Dependent Asymmetric Target Distributions for Self-Distillation Policy Optimization.pdf
- 2610.26397 - Bridged Self-Distillation for On-Policy Learning.pdf
- 2610.26856 - Reinforcement Learning with Visually Attributable On-Policy Self-Distillation.pdf
- 2610.27993 - Building Telecom Language Models with RSOD - Domain Data, Specialist Post-Training, Memory-Conscious Distillation, and Networking Evaluation.pdf