{"total":83,"rows":[{"id":"2207.10666","title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","created":"2022-07-21","cited_by_count":234,"area":null},{"id":"2105.08919","title":"Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation","created":"2021-05-19","cited_by_count":134,"area":"distill"},{"id":"2104.00676","title":"Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study","created":"2021-04-01","cited_by_count":51,"area":"distill"},{"id":"2206.06487","title":"The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation","created":"2022-06-13","cited_by_count":44,"area":"distill"},{"id":"2202.00155","title":"Fortuitous Forgetting in Connectionist Networks","created":"2022-02-01","cited_by_count":39,"area":null},{"id":"2206.14532","title":"Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?","created":"2022-06-29","cited_by_count":32,"area":"distill"},{"id":"2110.15210","title":"Towards Model Agnostic Federated Learning Using Knowledge Distillation","created":"2021-10-28","cited_by_count":31,"area":"distill"},{"id":"2104.09732","title":"Knowledge Distillation as Semiparametric Inference","created":"2021-04-20","cited_by_count":29,"area":"distill"},{"id":"2603.11178","title":"PACED: Distillation and On-Policy Self-Distillation at the Frontier of Student Competence","created":"2026-03-11","cited_by_count":28,"area":"distill"},{"id":"2105.14556","title":"Diversifying Dialog Generation via Adaptive Label Smoothing","created":"2021-05-30","cited_by_count":25,"area":null},{"id":"2401.08732","title":"Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information","created":"2024-01-16","cited_by_count":25,"area":"distill"},{"id":"2210.04427","title":"Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again","created":"2022-10-10","cited_by_count":23,"area":"distill"},{"id":"2202.09852","title":"Cross-Task Knowledge Distillation in Multi-Task Recommendation","created":"2022-02-20","cited_by_count":22,"area":"distill"},{"id":"2106.10494","title":"Teacher's pet: understanding and mitigating biases in distillation","created":"2021-06-19","cited_by_count":21,"area":"distill"},{"id":"2203.02485","title":"Better Supervisory Signals by Observing Learning Paths","created":"2022-03-04","cited_by_count":21,"area":"distill"},{"id":"2204.05957","title":"Localization Distillation for Object Detection","created":"2022-04-12","cited_by_count":19,"area":"distill"},{"id":"2208.08741","title":"Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification","created":"2022-08-18","cited_by_count":19,"area":"distill"},{"id":"2301.12245","title":"Supervision Complexity and its Role in Knowledge Distillation","created":"2023-01-28","cited_by_count":19,"area":"distill"},{"id":"2301.12923","title":"On student-teacher deviations in distillation: does it pay to disobey?","created":"2023-01-30","cited_by_count":16,"area":"distill"},{"id":"2603.13260","title":"Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation","created":"2026-02-25","cited_by_count":16,"area":"lr"},{"id":"2208.03763","title":"Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation","created":"2022-08-07","cited_by_count":14,"area":"distill"},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2302.05666","title":"Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels","created":"2023-02-11","cited_by_count":12,"area":"distill"},{"id":"2310.03295","title":"Can pre-trained models assist in dataset distillation?","created":"2023-10-05","cited_by_count":12,"area":null},{"id":"2102.13088","title":"Even your Teacher Needs Guidance: Ground-Truth Targets Dampen Regularization Imposed by Self-Distillation","created":"2021-02-25","cited_by_count":11,"area":"distill"},{"id":"2105.04181","title":"KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation","created":"2021-05-10","cited_by_count":11,"area":"distill"},{"id":"2305.08096","title":"Towards Understanding and Improving Knowledge Distillation for Neural Machine Translation","created":"2023-05-14","cited_by_count":10,"area":"distill"},{"id":"2104.03618","title":"MRI-based Alzheimer's disease prediction via distilling the knowledge in multi-modal data","created":"2021-04-08","cited_by_count":9,"area":null},{"id":"2210.05185","title":"Meta-Learning with Self-Improving Momentum Target","created":"2022-10-11","cited_by_count":9,"area":null},{"id":"2210.13459","title":"Adaptive Label Smoothing with Self-Knowledge in Natural Language Generation","created":"2022-10-22","cited_by_count":9,"area":"distill"},{"id":"2406.10861","title":"Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions","created":"2024-06-16","cited_by_count":9,"area":"distill"},{"id":"2302.08155","title":"Learning From Biased Soft Labels","created":"2023-02-16","cited_by_count":8,"area":"distill"},{"id":"2305.15734","title":"On the Impact of Knowledge Distillation for Model Interpretability","created":"2023-05-25","cited_by_count":8,"area":"distill"},{"id":"2309.08035","title":"Interpretability-Aware Vision Transformer","created":"2023-09-14","cited_by_count":8,"area":null},{"id":"2410.17020","title":"LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalization","created":"2024-10-22","cited_by_count":8,"area":null},{"id":"2102.06849","title":"Distilling Double Descent","created":"2021-02-13","cited_by_count":7,"area":"distill"},{"id":"2110.06961","title":"Language Modelling via Learning to Rank","created":"2021-10-13","cited_by_count":7,"area":null},{"id":"2206.06661","title":"Toward Student-Oriented Teacher Network Training For Knowledge Distillation","created":"2022-06-14","cited_by_count":7,"area":"distill"},{"id":"2307.08436","title":"DOT: A Distillation-Oriented Trainer","created":"2023-07-17","cited_by_count":7,"area":"distill"},{"id":"2404.14109","title":"CKD: Contrastive Knowledge Distillation from A Sample-wise Perspective","created":"2024-04-22","cited_by_count":7,"area":"distill"},{"id":"2404.12711","title":"Dynamic Temperature Knowledge Distillation","created":"2024-04-19","cited_by_count":6,"area":"distill"},{"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":"2107.00411","title":"Knowledge Distillation for Quality Estimation","created":"2021-07-01","cited_by_count":5,"area":"distill"},{"id":"2203.02651","title":"Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning","created":"2022-03-05","cited_by_count":5,"area":null},{"id":"2211.03946","title":"Understanding the Role of Mixup in Knowledge Distillation: An Empirical Study","created":"2022-11-08","cited_by_count":5,"area":"distill"},{"id":"2110.07879","title":"Advances and Challenges in Deep Lip Reading","created":"2021-10-15","cited_by_count":4,"area":null},{"id":"2210.12427","title":"Hard Gate Knowledge Distillation -- Leverage Calibration for Robust and Reliable Language Model","created":"2022-10-22","cited_by_count":4,"area":"distill"},{"id":"2309.14162","title":"Data Upcycling Knowledge Distillation for Image Super-Resolution","created":"2023-09-25","cited_by_count":4,"area":"distill"},{"id":"2310.07838","title":"Towards the Fundamental Limits of Knowledge Transfer over Finite Domains","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2405.13078","title":"Exploring Dark Knowledge under Various Teacher Capacities and Addressing Capacity Mismatch","created":"2024-05-21","cited_by_count":4,"area":"distill"},{"id":"2504.14694","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","created":"2025-04-20","cited_by_count":4,"area":"distill"},{"id":"2507.15911","title":"Local Dense Logit Relations for Enhanced Knowledge Distillation","created":"2025-07-21","cited_by_count":4,"area":"distill"},{"id":"2202.12598","title":"Bridging the Gap Between Patient-specific and Patient-independent Seizure Prediction via Knowledge Distillation","created":"2022-02-25","cited_by_count":3,"area":"distill"},{"id":"2402.15586","title":"Distilling Adversarial Robustness Using Heterogeneous Teachers","created":"2024-02-23","cited_by_count":3,"area":"distill"},{"id":"2507.22094","title":"Scaling and Distilling Transformer Models for sEMG","created":"2025-07-29","cited_by_count":3,"area":null},{"id":"2605.23857","title":"Strong Teacher Not Needed? On Distillation in LLM Pretraining","created":"2026-05-22","cited_by_count":3,"area":"distill"},{"id":"2108.10197","title":"Deploying a BERT-based Query-Title Relevance Classifier in a Production System: a View from the Trenches","created":"2021-08-23","cited_by_count":2,"area":null},{"id":"2309.09571","title":"Heterogeneous Generative Knowledge Distillation with Masked Image Modeling","created":"2023-09-18","cited_by_count":2,"area":"distill"},{"id":"2505.20836","title":"HAD: Hybrid Architecture Distillation Outperforms Teacher in Genomic Sequence Modeling","created":"2025-05-27","cited_by_count":2,"area":"distill"},{"id":"2605.18702","title":"Distilling Tabular Foundation Models for Structured Health Data","created":"2026-05-18","cited_by_count":2,"area":"distill"},{"id":"2204.11526","title":"Selective Cross-Task Distillation","created":"2022-04-25","cited_by_count":1,"area":"distill"},{"id":"2209.15496","title":"Using Knowledge Distillation to improve interpretable models in a retail banking context","created":"2022-09-30","cited_by_count":1,"area":"distill"},{"id":"2212.05225","title":"LEAD: Liberal Feature-based Distillation for Dense Retrieval","created":"2022-12-10","cited_by_count":1,"area":"distill"},{"id":"2404.15678","title":"Retrieval and Distill: A Temporal Data Shift-Free Paradigm for Online Recommendation System","created":"2024-04-24","cited_by_count":1,"area":null},{"id":"2404.18821","title":"Control Policy Correction Framework for Reinforcement Learning-based Energy Arbitrage Strategies","created":"2024-04-29","cited_by_count":1,"area":"deeprl"},{"id":"2409.02438","title":"Non-target Divergence Hypothesis: Toward Understanding Domain Gaps in Cross-Modal Knowledge Distillation","created":"2024-09-04","cited_by_count":1,"area":"distill"},{"id":"2411.00907","title":"On the Impact of White-box Deployment Strategies for Edge AI on Latency and Model Performance","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2501.04211","title":"CURing Large Models: Compression via CUR Decomposition","created":"2025-01-08","cited_by_count":1,"area":null},{"id":"2510.15516","title":"Revisiting Knowledge Distillation: The Hidden Role of Dataset Size","created":"2025-10-17","cited_by_count":1,"area":"distill"},{"id":"2511.04760","title":"When Data Falls Short: Grokking Below the Critical Threshold","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2605.20357","title":"Consistently Informative Soft-Label Temperature for Knowledge Distillation","created":"2026-05-19","cited_by_count":1,"area":"distill"},{"id":"2112.11447","title":"Multi-Modality Distillation via Learning the teacher's modality-level Gram Matrix","created":"2021-12-21","cited_by_count":0,"area":"distill"},{"id":"2306.15918","title":"On information captured by neural networks: connections with memorization and generalization","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2308.01098","title":"Towards Better Query Classification with Multi-Expert Knowledge Condensation in JD Ads Search","created":"2023-08-02","cited_by_count":0,"area":null},{"id":"2312.08585","title":"Unraveling Key Factors of Knowledge Distillation","created":"2023-12-14","cited_by_count":0,"area":"distill"},{"id":"2411.12098","title":"Federated Contrastive Learning of Graph-Level Representations","created":"2024-11-18","cited_by_count":0,"area":null},{"id":"2502.16762","title":"A Transformer-in-Transformer Network Utilizing Knowledge Distillation for Image Recognition","created":"2025-02-24","cited_by_count":0,"area":"distill"},{"id":"2509.12553","title":"iCD: A Implicit Clustering Distillation Mathod for Structural Information Mining","created":"2025-09-16","cited_by_count":0,"area":"distill"},{"id":"2510.13182","title":"Information-Theoretic Criteria for Knowledge Distillation in Multimodal Learning","created":"2025-10-15","cited_by_count":0,"area":"distill"},{"id":"2606.00306","title":"Rethinking the Role of Temperature in Large Language Model Distillation","created":"2026-05-29","cited_by_count":0,"area":"lr"},{"id":"2606.03052","title":"What Do Students Learn? A Feature-Level Analysis of Dark Knowledge","created":"2026-06-02","cited_by_count":0,"area":"distill"},{"id":"2607.15467","title":"ADS-C: Antidistillation Sampling for Classification","created":"2026-07-16","cited_by_count":0,"area":"distill"},{"id":"2609.33727","title":"A Statistical Perspective on Knowledge Distillation: Foundations, Classical Methods, and Large Language Model Extensions","created":"2026-09-27","cited_by_count":0,"area":"distill"}],"next_cursor":null}