{"total":84,"rows":[{"id":"2604.00626","title":"A Survey of On-Policy Distillation for Large Language Models","created":"2026-04-01","cited_by_count":163,"area":"distill"},{"id":"2603.11137","title":"Scaling Reasoning Efficiently via Relaxed On-Policy Distillation","created":"2026-03-11","cited_by_count":82,"area":"lr"},{"id":"2602.15260","title":"Fast and Effective On-policy Distillation from Reasoning Prefixes","created":"2026-02-16","cited_by_count":53,"area":"distill"},{"id":"2605.03677","title":"Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe","created":"2026-05-05","cited_by_count":49,"area":"distill"},{"id":"2605.08063","title":"Flow-OPD: On-Policy Distillation for Flow Matching Models","created":"2026-05-08","cited_by_count":34,"area":"diffusion"},{"id":"2606.01249","title":"Trust Region On-Policy Distillation","created":"2026-05-31","cited_by_count":30,"area":"distill"},{"id":"2510.24021","title":"SelecTKD: Selective Token-Weighted Knowledge Distillation for LLMs","created":"2025-10-28","cited_by_count":22,"area":"distill"},{"id":"2608.06296","title":"On-Policy Self-Distillation without Any Supervision","created":"2026-08-06","cited_by_count":17,"area":"lr"},{"id":"2607.04763","title":"Multi-Turn On-Policy Distillation with Prefix Replay","created":"2026-07-06","cited_by_count":15,"area":"agents"},{"id":"2605.30833","title":"Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation","created":"2026-05-29","cited_by_count":13,"area":"lr"},{"id":"2509.09284","title":"Tree-OPO: Off-policy Monte Carlo Tree-Guided Advantage Optimization for Multistep Reasoning","created":"2025-09-11","cited_by_count":12,"area":"lr"},{"id":"2605.07711","title":"SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation","created":"2026-05-08","cited_by_count":12,"area":"distill"},{"id":"2606.30626","title":"DOPD: Dual On-policy Distillation","created":"2026-06-29","cited_by_count":12,"area":"distill"},{"id":"2605.12652","title":"Multi-Rollout On-Policy Distillation via Peer Successes and Failures","created":"2026-05-12","cited_by_count":10,"area":"distill"},{"id":"2604.20244","title":"Hybrid Policy Distillation for LLMs","created":"2026-04-22","cited_by_count":9,"area":"distill"},{"id":"2606.09456","title":"Breaking the Tokenizer Barrier: On-Policy Distillation across Model Families","created":"2026-06-08","cited_by_count":9,"area":"distill"},{"id":"2509.06461","title":"Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning","created":"2025-09-08","cited_by_count":8,"area":"lr"},{"id":"2602.02848","title":"Zero Sum SVD: Balancing Loss Sensitivity for Low Rank LLM Compression","created":"2026-02-02","cited_by_count":8,"area":null},{"id":"2605.12798","title":"Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer","created":"2026-05-12","cited_by_count":8,"area":null},{"id":"2605.19433","title":"Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation","created":"2026-05-19","cited_by_count":8,"area":"lr"},{"id":"2607.22334","title":"Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization","created":"2026-07-24","cited_by_count":8,"area":"distill"},{"id":"2608.04419","title":"SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation","created":"2026-08-05","cited_by_count":8,"area":"distill"},{"id":"2512.04763","title":"MemLoRA: Distilling Expert Adapters for On-Device Memory Systems","created":"2025-12-04","cited_by_count":7,"area":null},{"id":"2606.23104","title":"ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation","created":"2026-06-22","cited_by_count":7,"area":"lr"},{"id":"2607.28590","title":"VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation","created":"2026-07-30","cited_by_count":7,"area":"distill"},{"id":"2512.20908","title":"Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation","created":"2025-12-24","cited_by_count":6,"area":"lr"},{"id":"2606.22793","title":"A Formula-Driven Survey and Research Agenda for On-Policy Distillation","created":"2026-06-22","cited_by_count":6,"area":"distill"},{"id":"2509.25100","title":"ORPO-Distill: Mixed-Policy Preference Optimization for Cross-Architecture LLM Distillation","created":"2025-09-29","cited_by_count":5,"area":"alignment"},{"id":"2509.25837","title":"Distillation of Large Language Models via Concrete Score Matching","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2511.21106","title":"EM-KD: Distilling Efficient Multimodal Large Language Model with Unbalanced Vision Tokens","created":"2025-11-26","cited_by_count":5,"area":"mllm"},{"id":"2608.03316","title":"Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging","created":"2026-08-04","cited_by_count":5,"area":"diffusion"},{"id":"2506.05695","title":"Being Strong Progressively! Enhancing Knowledge Distillation of Large Language Models through a Curriculum Learning Framework","created":"2025-06-06","cited_by_count":4,"area":"distill"},{"id":"2607.07050","title":"When Top-K Misses the Decision: Tool-Call Drift in Multi-Teacher On-Policy Distillation","created":"2026-07-08","cited_by_count":4,"area":"distill"},{"id":"2608.04349","title":"Poly-OPD: Heterogeneous Multi-Teacher On-Policy Distillation for Capability-Selectable Flow Models","created":"2026-08-05","cited_by_count":4,"area":"distill"},{"id":"2505.19427","title":"WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference","created":"2025-05-26","cited_by_count":3,"area":"moe"},{"id":"2509.22921","title":"Rethinking Large Language Model Distillation: A Constrained Markov Decision Process Perspective","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2602.12172","title":"Pedagogically-Inspired Data Synthesis for Language Model Knowledge Distillation","created":"2026-02-12","cited_by_count":3,"area":"synth"},{"id":"2605.05940","title":"Near-Policy: Accelerating On-Policy Distillation via Asynchronous Generation and Selective Packing","created":"2026-05-07","cited_by_count":3,"area":"distill"},{"id":"2509.18579","title":"Teaching Audio Models to Reason: A Unified Framework for Source- and Layer-wise Distillation","created":"2025-09-23","cited_by_count":2,"area":"lr"},{"id":"2510.15982","title":"AMiD: Knowledge Distillation for LLMs with $\\alpha$-mixture Assistant Distribution","created":"2025-10-13","cited_by_count":2,"area":"distill"},{"id":"2601.15394","title":"Memorization Dynamics in Knowledge Distillation for Language Models","created":"2026-01-21","cited_by_count":2,"area":"distill"},{"id":"2605.01374","title":"MTA: Multi-Granular Trajectory Alignment for Large Language Model Distillation","created":"2026-05-02","cited_by_count":2,"area":"alignment"},{"id":"2605.08737","title":"The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs","created":"2026-05-09","cited_by_count":2,"area":"distill"},{"id":"2606.09396","title":"PriFT: Prior-Support Guided Supervised Fine-Tuning","created":"2026-06-08","cited_by_count":2,"area":"lr"},{"id":"2606.29863","title":"KbSD: Knowledge Boundary aware Self-Distillation for Behavioral Calibration in Agentic Search","created":"2026-06-29","cited_by_count":2,"area":"agents"},{"id":"2607.06855","title":"Geometric Self-Distillation for Reasoning Generalization","created":"2026-07-07","cited_by_count":2,"area":"lr"},{"id":"2607.08255","title":"Compete Then Collaborate: Frontier AI Teachers Build a Verifiable Curriculum to Improve a Coding Student Beyond Imitation","created":"2026-07-09","cited_by_count":2,"area":null},{"id":"2609.23697","title":"Distill What You Trust: Reliability-Aware Multi-Teacher On-Policy Distillation","created":"2026-09-20","cited_by_count":2,"area":"distill"},{"id":"2605.04078","title":"Validity-Calibrated Reasoning Distillation","created":"2026-04-14","cited_by_count":1,"area":"lr"},{"id":"2605.11260","title":"Curriculum Learning-Guided Progressive Distillation in Large Language Models","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2605.15532","title":"DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation","created":"2026-05-15","cited_by_count":1,"area":"lr"},{"id":"2605.26872","title":"When the Strongest Teacher Is Not the Best Teacher: Student-Centric Answer Selection","created":"2026-05-26","cited_by_count":1,"area":"lr"},{"id":"2606.04694","title":"DuDi: Dual-Signal Distillation with Cross-Lingual Verbalizer","created":"2026-06-03","cited_by_count":1,"area":"distill"},{"id":"2608.14644","title":"DUET: Dual-Teacher On-Policy Distillation via Same-Weight Disagreement for Prohibition Compliance","created":"2026-07-29","cited_by_count":1,"area":"alignment"},{"id":"2609.12579","title":"SCOPE-OPSD: Fisher-Conditioned Privileged Subspaces for On-Policy Self-Distillation","created":"2026-09-11","cited_by_count":1,"area":"distill"},{"id":"2507.00054","title":"Enhancing Reasoning Capabilities in SLMs with Reward Guided Dataset Distillation","created":"2025-06-25","cited_by_count":0,"area":"lr"},{"id":"2602.13567","title":"DistillLens: Symmetric Knowledge Distillation Through Logit Lens","created":"2026-02-14","cited_by_count":0,"area":"mechinterp"},{"id":"2605.26246","title":"The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels Works","created":"2026-05-25","cited_by_count":0,"area":"distill"},{"id":"2607.05461","title":"AdaStop: Cost-Aware Early Stopping for DNN Test Selection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.08776","title":"A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions","created":"2026-05-05","cited_by_count":0,"area":"distill"},{"id":"2608.21229","title":"Beyond Attention Masks: Instruction Anchoring for Efficient In-Context Diffusion Generation","created":"2026-08-21","cited_by_count":0,"area":"diffusion"},{"id":"2608.26735","title":"Recovering General Capabilities via Uncertainty-Calibrated Multi-Teacher On-Policy Distillation","created":"2026-08-27","cited_by_count":0,"area":"distill"},{"id":"2609.29518","title":"CataOPD: Catalytic On-Policy Distillation for Large Language Model Reasoning","created":"2026-08-25","cited_by_count":0,"area":"lr"},{"id":"2609.34447","title":"Unbiased Top-$k$ Estimation for On-Policy Distillation","created":"2026-09-28","cited_by_count":0,"area":"distill"},{"id":"2609.34738","title":"Beyond Token Alignment: Event Completion for Cross-Tokenizer On-Policy Distillation","created":"2026-09-28","cited_by_count":0,"area":"distill"},{"id":"2609.35390","title":"Inductive Feedback for Mixed-Policy Distillation","created":"2026-09-28","cited_by_count":0,"area":"distill"},{"id":"2609.35505","title":"An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.36546","title":"Interactive-Policy Distillation with Bidirectional Propose-and-Verify","created":"2026-09-29","cited_by_count":0,"area":"distill"},{"id":"2609.36734","title":"Distilling What Matters: Confidence-Aware Selective Distillation for Large Language Models","created":"2026-09-29","cited_by_count":0,"area":"distill"},{"id":"2609.37377","title":"Beyond Prompt Count: How Data Shapes Transfer in On-Policy Distillation","created":"2026-09-29","cited_by_count":0,"area":"distill"},{"id":"2609.37500","title":"REVO: Rollout-Efficient Off-Policy Distillation via Variance-Guided Reuse","created":"2026-09-28","cited_by_count":0,"area":"distill"},{"id":"2609.38666","title":"Understanding Off- vs On-Policy Distillation: A Tale of Distinct Training Objectives","created":"2026-09-29","cited_by_count":0,"area":"distill"},{"id":"2609.39687","title":"Better Supervision Is Nearby: Neighborhood On-Policy Self-Distillation","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.00332","title":"The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.03372","title":"SCAD: Structured Credit Assignment and Distillation for Long-Horizon Agents","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.04950","title":"How Should Teachers Be Prepared? RL on Student-Induced States for On-Policy Distillation","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.05974","title":"Transfer-Stratified On-Policy Distillation for RL-Improved Reasoning Teachers","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.11332","title":"ReCal: Calibrating Structured Pruning for On-Policy Distillation Recovery","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.13257","title":"CAST: Credit Alignment for Cross-Tokenizer On-Policy Distillation","created":"2026-10-09","cited_by_count":0,"area":"distill"},{"id":"2610.13521","title":"Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation","created":"2026-10-09","cited_by_count":0,"area":"distill"},{"id":"2610.15589","title":"The Gradient That Top-k Distillation Never Computes","created":"2026-10-11","cited_by_count":0,"area":"distill"},{"id":"2610.16543","title":"Overtaught, Underlearned: Learner-Centered Distillation from Multi-Agent Discussion","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18011","title":"Correcting or Continuing? What On-Policy Distillation Learns from Student Errors","created":"2026-10-13","cited_by_count":0,"area":"distill"},{"id":"2610.19601","title":"PA1-OPD: One-Step Prefix-Augmented On-Policy Distillation for Language Model Pretraining","created":"2026-10-14","cited_by_count":0,"area":"distill"}],"next_cursor":null}