{"total":33,"rows":[{"id":"2306.08543","title":"MiniLLM: On-Policy Distillation of Large Language Models","created":"2023-06-14","cited_by_count":139,"area":"distill"},{"id":"2402.13669","title":"Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning","created":"2024-02-21","cited_by_count":96,"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":"2410.17215","title":"MiniPLM: Knowledge Distillation for Pre-Training Language Models","created":"2024-10-22","cited_by_count":29,"area":"distill"},{"id":"2305.08776","title":"Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models","created":"2023-05-15","cited_by_count":27,"area":"distill"},{"id":"2406.17328","title":"Dual-Space Knowledge Distillation for Large Language Models","created":"2024-06-25","cited_by_count":25,"area":"distill"},{"id":"2308.06744","title":"Token-Scaled Logit Distillation for Ternary Weight Generative Language Models","created":"2023-08-13","cited_by_count":20,"area":"distill"},{"id":"2305.02031","title":"A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training","created":"2023-05-03","cited_by_count":16,"area":"distill"},{"id":"2406.05322","title":"Teaching-Assistant-in-the-Loop: Improving Knowledge Distillation from Imperfect Teacher Models in Low-Budget Scenarios","created":"2024-06-08","cited_by_count":12,"area":"distill"},{"id":"2502.11306","title":"Smoothing Out Hallucinations: Mitigating LLM Hallucination with Smoothed Knowledge Distillation","created":"2025-02-16","cited_by_count":10,"area":"distill"},{"id":"2210.01213","title":"Robust Active Distillation","created":"2022-10-03","cited_by_count":9,"area":"distill"},{"id":"2408.10210","title":"A Survey on Symbolic Knowledge Distillation of Large Language Models","created":"2024-07-12","cited_by_count":9,"area":"distill"},{"id":"2305.19412","title":"Are Large Kernels Better Teachers than Transformers for ConvNets?","created":"2023-05-30","cited_by_count":8,"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":"2212.08974","title":"3D Point Cloud Pre-training with Knowledge Distillation from 2D Images","created":"2022-12-17","cited_by_count":7,"area":"distill"},{"id":"2305.03433","title":"Towards Applying Powerful Large AI Models in Classroom Teaching: Opportunities, Challenges and Prospects","created":"2023-05-05","cited_by_count":6,"area":"distill"},{"id":"2411.19638","title":"LLM Teacher-Student Framework for Text Classification With No Manually Annotated Data: A Case Study in IPTC News Topic Classification","created":"2024-11-29","cited_by_count":6,"area":"distill"},{"id":"2411.06448","title":"Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation","created":"2024-11-10","cited_by_count":5,"area":"distill"},{"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":"2211.16740","title":"Explicit Knowledge Transfer for Weakly-Supervised Code Generation","created":"2022-11-30","cited_by_count":4,"area":"distill"},{"id":"2409.12586","title":"Efficient Knowledge Distillation: Empowering Small Language Models with Teacher Model Insights","created":"2024-09-19","cited_by_count":4,"area":"distill"},{"id":"2504.16056","title":"Honey, I Shrunk the Language Model: Impact of Knowledge Distillation Methods on Performance and Explainability","created":"2025-04-22","cited_by_count":2,"area":"distill"},{"id":"2505.01693","title":"High-Fidelity Pseudo-label Generation by Large Language Models for Training Robust Radiology Report Classifiers","created":"2025-05-03","cited_by_count":2,"area":"distill"},{"id":"2409.18565","title":"Harmonizing knowledge Transfer in Neural Network with Unified Distillation","created":"2024-09-27","cited_by_count":1,"area":"distill"},{"id":"2410.00558","title":"AMR-Evol: Adaptive Modular Response Evolution Elicits Better Knowledge Distillation for Large Language Models in Code Generation","created":"2024-10-01","cited_by_count":1,"area":"distill"},{"id":"2510.06502","title":"GUIDE: Guided Initialization and Distillation of Embeddings","created":"2025-10-07","cited_by_count":1,"area":"distill"},{"id":"2310.13418","title":"GenDistiller: Distilling Pre-trained Language Models based on Generative Models","created":"2023-10-20","cited_by_count":0,"area":"distill"},{"id":"2511.07110","title":"Two Heads are Better than One: Distilling Large Language Model Features Into Small Models with Feature Decomposition and Mixture","created":"2025-11-10","cited_by_count":0,"area":"distill"},{"id":"2511.19495","title":"A Systematic Study of Compression Ordering for Large Language Models","created":"2025-11-23","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":"2607.08161","title":"SQuaD-SQL: Efficient Text-to-SQL with Small Language Models via LLM-Guided Knowledge Distillation","created":"2026-07-09","cited_by_count":0,"area":"distill"},{"id":"2609.14715","title":"Depth and Scale in the Sub-150M Regime: JugnuLM-53M vs JugnuLM-110M","created":"2026-09-13","cited_by_count":0,"area":"distill"}],"next_cursor":null}