{"total":114,"rows":[{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2603.07079","title":"Entropy-Aware On-Policy Distillation of Language Models","created":"2026-03-07","cited_by_count":175,"area":"distill"},{"id":"2310.08461","title":"DistillSpec: Improving Speculative Decoding via Knowledge Distillation","created":"2023-10-12","cited_by_count":165,"area":"inference"},{"id":"2402.03898","title":"DistiLLM: Towards Streamlined Distillation for Large Language Models","created":"2024-02-06","cited_by_count":163,"area":"distill"},{"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":"2503.07067","title":"DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs","created":"2025-03-10","cited_by_count":84,"area":null},{"id":"2410.20672","title":"Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA","created":"2024-10-28","cited_by_count":78,"area":null},{"id":"2410.21035","title":"Beyond Autoregression: Fast LLMs via Self-Distillation Through Time","created":"2024-10-28","cited_by_count":78,"area":"diffusion"},{"id":"2404.02657","title":"Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models","created":"2024-04-03","cited_by_count":65,"area":"lr"},{"id":"2407.01885","title":"Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application","created":"2024-07-02","cited_by_count":56,"area":"distill"},{"id":"2605.15155","title":"Self-Distilled Agentic Reinforcement Learning","created":"2026-05-14","cited_by_count":55,"area":"agents"},{"id":"2601.07155","title":"Stable On-Policy Distillation through Adaptive Target Reformulation","created":"2026-01-12","cited_by_count":53,"area":"distill"},{"id":"2311.07052","title":"Towards the Law of Capacity Gap in Distilling Language Models","created":"2023-11-13","cited_by_count":44,"area":"distill"},{"id":"2402.11890","title":"Revisiting Knowledge Distillation for Autoregressive Language Models","created":"2024-02-19","cited_by_count":42,"area":"distill"},{"id":"2410.16236","title":"LLaVA-KD: A Framework of Distilling Multimodal Large Language Models","created":"2024-10-21","cited_by_count":40,"area":"mllm"},{"id":"2412.14528","title":"Multi-Level Optimal Transport for Universal Cross-Tokenizer Knowledge Distillation on Language Models","created":"2024-12-19","cited_by_count":36,"area":"distill"},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2605.21606","title":"When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning","created":"2026-05-20","cited_by_count":30,"area":"distill"},{"id":"2410.17215","title":"MiniPLM: Knowledge Distillation for Pre-Training Language Models","created":"2024-10-22","cited_by_count":29,"area":"distill"},{"id":"2407.19409","title":"LLAVADI: What Matters For Multimodal Large Language Models Distillation","created":"2024-07-28","cited_by_count":26,"area":"mllm"},{"id":"2606.22600","title":"On the Position Bias of On-Policy Distillation","created":"2026-06-21","cited_by_count":26,"area":"lr"},{"id":"2406.17328","title":"Dual-Space Knowledge Distillation for Large Language Models","created":"2024-06-25","cited_by_count":25,"area":"distill"},{"id":"2502.00883","title":"SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters","created":"2025-02-02","cited_by_count":25,"area":"alignment"},{"id":"2505.04560","title":"ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\\alpha$-$\\beta$-Divergence","created":"2025-05-07","cited_by_count":23,"area":"distill"},{"id":"2403.00858","title":"Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMs","created":"2024-02-29","cited_by_count":22,"area":"inference"},{"id":"2501.16937","title":"TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models","created":"2025-01-28","cited_by_count":22,"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":"2406.19774","title":"Direct Preference Knowledge Distillation for Large Language Models","created":"2024-06-28","cited_by_count":21,"area":"alignment"},{"id":"2311.01070","title":"Multilingual DistilWhisper: Efficient Distillation of Multi-task Speech Models via Language-Specific Experts","created":"2023-11-02","cited_by_count":17,"area":null},{"id":"2503.02832","title":"AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation","created":"2025-03-04","cited_by_count":17,"area":"alignment"},{"id":"2503.16870","title":"Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs","created":"2025-03-21","cited_by_count":16,"area":"distill"},{"id":"2402.17110","title":"Sinkhorn Distance Minimization for Knowledge Distillation","created":"2024-02-27","cited_by_count":15,"area":"distill"},{"id":"2410.18779","title":"A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2412.18934","title":"Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference","created":"2024-12-25","cited_by_count":13,"area":"inference"},{"id":"2608.05987","title":"AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning","created":"2026-08-06","cited_by_count":12,"area":"agents"},{"id":"2406.02886","title":"PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs","created":"2024-06-05","cited_by_count":11,"area":"distill"},{"id":"2409.12545","title":"Enhancing Knowledge Distillation of Large Language Models through Efficient Multi-Modal Distribution Alignment","created":"2024-09-19","cited_by_count":11,"area":"distill"},{"id":"2410.05165","title":"Efficient Inference for Large Language Model-based Generative Recommendation","created":"2024-10-07","cited_by_count":11,"area":null},{"id":"2601.21968","title":"OVD: On-policy Verbal Distillation","created":"2026-01-29","cited_by_count":11,"area":"lr"},{"id":"2503.07807","title":"Training Domain Draft Models for Speculative Decoding: Best Practices and Insights","created":"2025-03-10","cited_by_count":10,"area":"inference"},{"id":"2504.15027","title":"DistilQwen2.5: Industrial Practices of Training Distilled Open Lightweight Language Models","created":"2025-04-21","cited_by_count":10,"area":null},{"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":"2410.19503","title":"SWITCH: Studying with Teacher for Knowledge Distillation of Large Language Models","created":"2024-10-25","cited_by_count":9,"area":"distill"},{"id":"2505.13111","title":"Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation","created":"2025-05-19","cited_by_count":9,"area":"distill"},{"id":"2604.20244","title":"Hybrid Policy Distillation for LLMs","created":"2026-04-22","cited_by_count":9,"area":"distill"},{"id":"2504.11426","title":"A Dual-Space Framework for General Knowledge Distillation of Large Language Models","created":"2025-04-15","cited_by_count":8,"area":"distill"},{"id":"2510.19779","title":"AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders","created":"2025-10-22","cited_by_count":8,"area":"inference"},{"id":"2607.13124","title":"ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation","created":"2026-07-14","cited_by_count":8,"area":"distill"},{"id":"2607.22334","title":"Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization","created":"2026-07-24","cited_by_count":8,"area":"distill"},{"id":"2402.09773","title":"NutePrune: Efficient Progressive Pruning with Numerous Teachers for Large Language Models","created":"2024-02-15","cited_by_count":7,"area":null},{"id":"2410.10141","title":"Temperature-Centric Investigation of Speculative Decoding with Knowledge Distillation","created":"2024-10-14","cited_by_count":7,"area":"inference"},{"id":"2604.03873","title":"SODA: Semi On-Policy Black-Box Distillation for Large Language Models","created":"2026-04-04","cited_by_count":7,"area":"distill"},{"id":"2606.01476","title":"OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification","created":"2026-05-31","cited_by_count":7,"area":"lr"},{"id":"2310.01717","title":"Ensemble Distillation for Unsupervised Constituency Parsing","created":"2023-10-03","cited_by_count":6,"area":null},{"id":"2502.12947","title":"Every Expert Matters: Towards Effective Knowledge Distillation for Mixture-of-Experts Language Models","created":"2025-02-18","cited_by_count":6,"area":"moe"},{"id":"2503.13440","title":"MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling","created":"2025-03-17","cited_by_count":6,"area":"mllm"},{"id":"2504.13825","title":"Feature Alignment and Representation Transfer in Knowledge Distillation for Large Language Models","created":"2025-04-18","cited_by_count":6,"area":"distill"},{"id":"2502.04499","title":"Revisiting Intermediate-Layer Matching in Knowledge Distillation: Layer-Selection Strategy Doesn't Matter (Much)","created":"2025-02-06","cited_by_count":5,"area":"distill"},{"id":"2502.17927","title":"Advantage-Guided Distillation for Preference Alignment in Small Language Models","created":"2025-02-25","cited_by_count":5,"area":"alignment"},{"id":"2502.19982","title":"Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models","created":"2025-02-27","cited_by_count":5,"area":"safety"},{"id":"2509.25837","title":"Distillation of Large Language Models via Concrete Score Matching","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2602.09483","title":"Beyond Next-Token Alignment: Distilling Multimodal Large Language Models via Token Interactions","created":"2026-02-10","cited_by_count":5,"area":"mllm"},{"id":"2602.21669","title":"DWA-KD: Dual-Space Weighting and Time-Warped Alignment for Cross-Tokenizer Knowledge Distillation","created":"2026-02-25","cited_by_count":5,"area":"distill"},{"id":"2311.13934","title":"Robustness-Reinforced Knowledge Distillation with Correlation Distance and Network Pruning","created":"2023-11-23","cited_by_count":4,"area":"distill"},{"id":"2502.16806","title":"CoT2Align: Cross-Chain of Thought Distillation via Optimal Transport Alignment for Language Models with Different Tokenizers","created":"2025-02-24","cited_by_count":4,"area":"lr"},{"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":"2507.02659","title":"OmniDraft: A Cross-vocabulary, Online Adaptive Drafter for On-device Speculative Decoding","created":"2025-07-03","cited_by_count":4,"area":"inference"},{"id":"2603.23911","title":"Self-Distillation for Multi-Token Prediction","created":"2026-03-25","cited_by_count":4,"area":"distill"},{"id":"2604.04987","title":"Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling","created":"2026-04-05","cited_by_count":4,"area":"inference"},{"id":"2409.12500","title":"LLMR: Knowledge Distillation with a Large Language Model-Induced Reward","created":"2024-09-19","cited_by_count":3,"area":"distill"},{"id":"2409.12512","title":"Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models","created":"2024-09-19","cited_by_count":3,"area":"distill"},{"id":"2504.19024","title":"KETCHUP: K-Step Return Estimation for Sequential Knowledge Distillation","created":"2025-04-26","cited_by_count":3,"area":"distill"},{"id":"2605.01205","title":"SRA: Span Representation Alignment for Large Language Model Distillation","created":"2026-05-02","cited_by_count":3,"area":"alignment"},{"id":"2608.03092","title":"SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation","created":"2026-08-04","cited_by_count":3,"area":"alignment"},{"id":"2405.00966","title":"Efficient Compression of Multitask Multilingual Speech Models","created":"2024-05-02","cited_by_count":2,"area":null},{"id":"2407.10068","title":"Multi-Granularity Semantic Revision for Large Language Model Distillation","created":"2024-07-14","cited_by_count":2,"area":"distill"},{"id":"2410.11371","title":"Learning from Imperfect Data: Towards Efficient Knowledge Distillation of Autoregressive Language Models for Text-to-SQL","created":"2024-10-15","cited_by_count":2,"area":"distill"},{"id":"2502.01491","title":"Memorization Inheritance in Sequence-Level Knowledge Distillation for Neural Machine Translation","created":"2025-02-03","cited_by_count":2,"area":"distill"},{"id":"2505.20335","title":"Language Model Distillation: A Temporal Difference Imitation Learning Perspective","created":"2025-05-24","cited_by_count":2,"area":"offlinerl"},{"id":"2505.22811","title":"Highly Efficient and Effective LLMs with Multi-Boolean Architectures","created":"2025-05-28","cited_by_count":2,"area":null},{"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":"2602.15845","title":"KD4MT: A Survey of Knowledge Distillation for Machine Translation","created":"2026-01-22","cited_by_count":2,"area":"distill"},{"id":"2604.03192","title":"Reliability Gated Multi-Teacher Distillation for Low Resource Abstractive Summarization","created":"2026-04-03","cited_by_count":2,"area":"distill"},{"id":"2606.06078","title":"Knowledge Distillation for Visual Autoregressive Models","created":"2026-06-04","cited_by_count":2,"area":"distill"},{"id":"2608.27448","title":"TTPO: Test-Time Policy Optimization","created":"2026-08-27","cited_by_count":2,"area":"lr"},{"id":"2403.00144","title":"EBBS: An Ensemble with Bi-Level Beam Search for Zero-Shot Machine Translation","created":"2024-02-29","cited_by_count":1,"area":null},{"id":"2403.13681","title":"Ayn: A Tiny yet Competitive Indian Legal Language Model Pretrained from Scratch","created":"2024-03-20","cited_by_count":1,"area":null},{"id":"2602.12674","title":"$\\mathcal{X}$-KD: General Experiential Knowledge Distillation for Large Language Models","created":"2026-02-13","cited_by_count":1,"area":"distill"},{"id":"2603.24518","title":"TuneShift-KD: Knowledge Distillation and Transfer for Fine-tuned Models","created":"2026-03-25","cited_by_count":1,"area":"distill"},{"id":"2604.18963","title":"Distillation Traps and Guards: A Calibration Knob for LLM Distillability","created":"2026-04-21","cited_by_count":1,"area":"distill"},{"id":"2605.15532","title":"DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation","created":"2026-05-15","cited_by_count":1,"area":"lr"},{"id":"2606.00755","title":"Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning","created":"2026-05-30","cited_by_count":1,"area":"lr"},{"id":"2607.24522","title":"FlowCTS: On-policy Continuous Trajectory Supervision of Flow Models","created":"2026-07-27","cited_by_count":1,"area":"distill"},{"id":"2505.18952","title":"Online Knowledge Distillation with Reward Guidance","created":"2025-05-25","cited_by_count":0,"area":"alignment"},{"id":"2506.12403","title":"Bridging the Digital Divide: Small Language Models as a Pathway for Physics and Photonics Education in Underdeveloped Regions","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2508.04225","title":"Symmetric Behavior Regularized Policy Optimization","created":"2025-08-06","cited_by_count":0,"area":"offlinerl"},{"id":"2511.01354","title":"Thinking with DistilQwen: A Tale of Four Distilled Reasoning and Reward Model Series","created":"2025-11-03","cited_by_count":0,"area":"lr"},{"id":"2601.01484","title":"SGD-Based Knowledge Distillation with Bayesian Teachers: Theory and Guidelines","created":"2026-01-04","cited_by_count":0,"area":"distill"},{"id":"2601.10114","title":"Following the Teacher's Footsteps: Scheduled Checkpoint Distillation for Domain-Specific LLMs","created":"2026-01-15","cited_by_count":0,"area":"distill"},{"id":"2602.13567","title":"DistillLens: Symmetric Knowledge Distillation Through Logit Lens","created":"2026-02-14","cited_by_count":0,"area":"mechinterp"}],"next_cursor":"100"}