{"total":173,"rows":[{"id":"2106.14448","title":"R-Drop: Regularized Dropout for Neural Networks","created":"2021-06-28","cited_by_count":202,"area":null},{"id":"2106.05945","title":"Does Knowledge Distillation Really Work?","created":"2021-06-10","cited_by_count":190,"area":"distill"},{"id":"2203.14001","title":"Knowledge Distillation with the Reused Teacher Classifier","created":"2022-03-26","cited_by_count":141,"area":"distill"},{"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":"2402.07043","title":"A Tale of Tails: Model Collapse as a Change of Scaling Laws","created":"2024-02-10","cited_by_count":130,"area":"synth"},{"id":"2204.09560","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","created":"2022-04-20","cited_by_count":125,"area":null},{"id":"2110.08529","title":"Sharpness-Aware Minimization Improves Language Model Generalization","created":"2021-10-16","cited_by_count":108,"area":null},{"id":"2412.01951","title":"Self-Improvement in Language Models: The Sharpening Mechanism","created":"2024-12-02","cited_by_count":104,"area":"synth"},{"id":"2402.07712","title":"Model Collapse Demystified: The Case of Regression","created":"2024-02-12","cited_by_count":82,"area":"synth"},{"id":"2210.07686","title":"Learning Generalizable Models for Vehicle Routing Problems via Knowledge Distillation","created":"2022-10-14","cited_by_count":62,"area":"distill"},{"id":"2102.09517","title":"Essentials for Class Incremental Learning","created":"2021-02-18","cited_by_count":57,"area":null},{"id":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57,"area":null},{"id":"2102.12252","title":"Localization Distillation for Dense Object Detection","created":"2021-02-24","cited_by_count":55,"area":"distill"},{"id":"2410.16713","title":"Collapse or Thrive? Perils and Promises of Synthetic Data in a Self-Generating World","created":"2024-10-22","cited_by_count":52,"area":null},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2106.06770","title":"What can linearized neural networks actually say about generalization?","created":"2021-06-12","cited_by_count":49,"area":null},{"id":"2406.07515","title":"Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification","created":"2024-06-11","cited_by_count":45,"area":"synth"},{"id":"2106.06168","title":"Generate, Annotate, and Learn: NLP with Synthetic Text","created":"2021-06-11","cited_by_count":42,"area":"distill"},{"id":"2405.15116","title":"Quantifying the Gain in Weak-to-Strong Generalization","created":"2024-05-24","cited_by_count":41,"area":null},{"id":"2203.06321","title":"Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation","created":"2022-03-12","cited_by_count":39,"area":"distill"},{"id":"2110.02424","title":"Spectral Bias in Practice: The Role of Function Frequency in Generalization","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2110.15210","title":"Towards Model Agnostic Federated Learning Using Knowledge Distillation","created":"2021-10-28","cited_by_count":31,"area":"distill"},{"id":"2111.14655","title":"FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization","created":"2021-11-29","cited_by_count":31,"area":null},{"id":"2103.09154","title":"Leveraging Recent Advances in Deep Learning for Audio-Visual Emotion Recognition","created":"2021-03-16","cited_by_count":30,"area":null},{"id":"2209.13476","title":"Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labels","created":"2022-09-27","cited_by_count":30,"area":null},{"id":"2104.09732","title":"Knowledge Distillation as Semiparametric Inference","created":"2021-04-20","cited_by_count":29,"area":"distill"},{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"area":null},{"id":"2204.08397","title":"Fast and Memory-Efficient Network Towards Efficient Image Super-Resolution","created":"2022-04-18","cited_by_count":27,"area":null},{"id":"2208.12807","title":"Towards Federated Learning against Noisy Labels via Local Self-Regularization","created":"2022-08-25","cited_by_count":26,"area":null},{"id":"2410.22812","title":"Universality of the $\\pi^2/6$ Pathway in Avoiding Model Collapse","created":"2024-10-30","cited_by_count":26,"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":"2412.14689","title":"How to Synthesize Text Data without Model Collapse?","created":"2024-12-19","cited_by_count":25,"area":"synth"},{"id":"2105.09750","title":"Anchor-based Plain Net for Mobile Image Super-Resolution","created":"2021-05-20","cited_by_count":24,"area":null},{"id":"2206.08491","title":"Revisiting Self-Distillation","created":"2022-06-17","cited_by_count":24,"area":"distill"},{"id":"2207.02099","title":"An Empirical Study of Implicit Regularization in Deep Offline RL","created":"2022-07-05","cited_by_count":24,"area":"offlinerl"},{"id":"2210.13014","title":"Geometric Knowledge Distillation: Topology Compression for Graph Neural Networks","created":"2022-10-24","cited_by_count":22,"area":"distill"},{"id":"2410.18837","title":"High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws","created":"2024-10-24","cited_by_count":22,"area":"distill"},{"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":"2106.10494","title":"Teacher's pet: understanding and mitigating biases in distillation","created":"2021-06-19","cited_by_count":21,"area":"distill"},{"id":"2108.04228","title":"Iterative Distillation for Better Uncertainty Estimates in Multitask Emotion Recognition","created":"2021-07-21","cited_by_count":21,"area":null},{"id":"2301.13304","title":"Understanding Self-Distillation in the Presence of Label Noise","created":"2023-01-30","cited_by_count":21,"area":"distill"},{"id":"2109.13059","title":"Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations","created":"2021-09-27","cited_by_count":20,"area":null},{"id":"2306.10687","title":"Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillation","created":"2023-06-19","cited_by_count":20,"area":"distill"},{"id":"2111.12172","title":"Multi-label Iterated Learning for Image Classification with Label Ambiguity","created":"2021-11-23","cited_by_count":19,"area":null},{"id":"2204.05957","title":"Localization Distillation for Object Detection","created":"2022-04-12","cited_by_count":19,"area":"distill"},{"id":"2206.04672","title":"Overcoming the Spectral Bias of Neural Value Approximation","created":"2022-06-09","cited_by_count":19,"area":null},{"id":"2301.12245","title":"Supervision Complexity and its Role in Knowledge Distillation","created":"2023-01-28","cited_by_count":19,"area":"distill"},{"id":"2203.14577","title":"Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?","created":"2022-03-28","cited_by_count":18,"area":null},{"id":"2106.02654","title":"Churn Reduction via Distillation","created":"2021-06-04","cited_by_count":17,"area":null},{"id":"2404.02145","title":"Iterated Learning Improves Compositionality in Large Vision-Language Models","created":"2024-04-02","cited_by_count":17,"area":"mllm"},{"id":"2404.04286","title":"Bias Amplification in Language Model Evolution: An Iterated Learning Perspective","created":"2024-04-04","cited_by_count":17,"area":null},{"id":"2410.05101","title":"CR-CTC: Consistency regularization on CTC for improved speech recognition","created":"2024-10-07","cited_by_count":17,"area":null},{"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":"2410.04638","title":"Provable Weak-to-Strong Generalization via Benign Overfitting","created":"2024-10-06","cited_by_count":16,"area":"distill"},{"id":"2310.18777","title":"Improving Compositional Generalization Using Iterated Learning and Simplicial Embeddings","created":"2023-10-28","cited_by_count":15,"area":null},{"id":"2407.04600","title":"Understanding the Gains from Repeated Self-Distillation","created":"2024-07-05","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":"2111.12958","title":"Self-Distilled Self-Supervised Representation Learning","created":"2021-11-25","cited_by_count":14,"area":"distill"},{"id":"2112.01653","title":"Learning Curves for Continual Learning in Neural Networks: Self-Knowledge Transfer and Forgetting","created":"2021-12-03","cited_by_count":14,"area":null},{"id":"2305.14783","title":"Disentangled Phonetic Representation for Chinese Spelling Correction","created":"2023-05-24","cited_by_count":14,"area":null},{"id":"2405.17258","title":"$\\textit{Trans-LoRA}$: towards data-free Transferable Parameter Efficient Finetuning","created":"2024-05-27","cited_by_count":13,"area":null},{"id":"2405.18756","title":"Provable Contrastive Continual Learning","created":"2024-05-29","cited_by_count":13,"area":null},{"id":"2407.18041","title":"How to Train the Teacher Model for Effective Knowledge Distillation","created":"2024-07-25","cited_by_count":13,"area":"distill"},{"id":"2110.08220","title":"Combining Diverse Feature Priors","created":"2021-10-15","cited_by_count":12,"area":null},{"id":"2203.14649","title":"Knowledge Distillation: Bad Models Can Be Good Role Models","created":"2022-03-28","cited_by_count":12,"area":"distill"},{"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":"2502.05075","title":"Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension","created":"2025-02-07","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":"2303.08983","title":"Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement","created":"2023-03-15","cited_by_count":11,"area":null},{"id":"2305.17581","title":"Knowledge Distillation Performs Partial Variance Reduction","created":"2023-05-27","cited_by_count":11,"area":"distill"},{"id":"2210.02871","title":"Self-Distillation for Further Pre-training of Transformers","created":"2022-09-30","cited_by_count":9,"area":"distill"},{"id":"2303.12915","title":"Self-distillation for surgical action recognition","created":"2023-03-22","cited_by_count":9,"area":"distill"},{"id":"2404.13518","title":"Reliable Model Watermarking: Defending Against Theft without Compromising on Evasion","created":"2024-04-21","cited_by_count":9,"area":"safety"},{"id":"2303.14666","title":"Generalization Matters: Loss Minima Flattening via Parameter Hybridization for Efficient Online Knowledge Distillation","created":"2023-03-26","cited_by_count":8,"area":"distill"},{"id":"2304.10113","title":"SATA: Source Anchoring and Target Alignment Network for Continual Test Time Adaptation","created":"2023-04-20","cited_by_count":8,"area":null},{"id":"2507.10935","title":"GeoDistill: Geometry-Guided Self-Distillation for Weakly Supervised Cross-View Localization","created":"2025-07-15","cited_by_count":8,"area":null},{"id":"2102.06849","title":"Distilling Double Descent","created":"2021-02-13","cited_by_count":7,"area":"distill"},{"id":"2109.07049","title":"Self-Training with Differentiable Teacher","created":"2021-09-15","cited_by_count":7,"area":"distill"},{"id":"2206.06661","title":"Toward Student-Oriented Teacher Network Training For Knowledge Distillation","created":"2022-06-14","cited_by_count":7,"area":"distill"},{"id":"2210.14636","title":"Fast Yet Effective Speech Emotion Recognition with Self-distillation","created":"2022-10-26","cited_by_count":7,"area":"distill"},{"id":"2509.01649","title":"Distilled Pretraining: A modern lens of Data, In-Context Learning and Test-Time Scaling","created":"2025-09-01","cited_by_count":7,"area":"lr"},{"id":"2112.08772","title":"Sharpness-Aware Minimization with Dynamic Reweighting","created":"2021-12-16","cited_by_count":6,"area":null},{"id":"2302.12091","title":"Random Teachers are Good Teachers","created":"2023-02-23","cited_by_count":6,"area":"distill"},{"id":"2302.14643","title":"Graph-based Knowledge Distillation: A survey and experimental evaluation","created":"2023-02-27","cited_by_count":6,"area":"distill"},{"id":"2303.05093","title":"Improving Video Retrieval by Adaptive Margin","created":"2023-03-09","cited_by_count":6,"area":null},{"id":"2304.04858","title":"Simulated Annealing in Early Layers Leads to Better Generalization","created":"2023-04-10","cited_by_count":6,"area":null},{"id":"2402.00084","title":"EPSD: Early Pruning with Self-Distillation for Efficient Model Compression","created":"2024-01-31","cited_by_count":6,"area":"distill"},{"id":"2507.00075","title":"Theoretical Modeling of Large Language Model Self-Improvement Training Dynamics Through Solver-Verifier Gap","created":"2025-06-29","cited_by_count":6,"area":"synth"},{"id":"2211.15774","title":"Decentralized Learning with Multi-Headed Distillation","created":"2022-11-28","cited_by_count":5,"area":null},{"id":"2306.05278","title":"Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-training","created":"2023-06-08","cited_by_count":5,"area":null},{"id":"2403.01479","title":"Align-to-Distill: Trainable Attention Alignment for Knowledge Distillation in Neural Machine Translation","created":"2024-03-03","cited_by_count":5,"area":"distill"},{"id":"2406.11206","title":"Retraining with Predicted Hard Labels Provably Increases Model Accuracy","created":"2024-06-17","cited_by_count":5,"area":null},{"id":"2411.01431","title":"Efficient Deep Learning Infrastructures for Embedded Computing Systems: A Comprehensive Survey and Future Envision","created":"2024-11-03","cited_by_count":5,"area":null},{"id":"2501.15014","title":"On Accelerating Edge AI: Optimizing Resource-Constrained Environments","created":"2025-01-25","cited_by_count":5,"area":null},{"id":"2503.01754","title":"SDRT: Enhance Vision-Language Models by Self-Distillation with Diverse Reasoning Traces","created":"2025-03-03","cited_by_count":5,"area":"lr"},{"id":"2507.17668","title":"How Should We Meta-Learn Reinforcement Learning Algorithms?","created":"2025-07-23","cited_by_count":5,"area":"deeprl"},{"id":"2204.02004","title":"Bimodal Distributed Binarized Neural Networks","created":"2022-04-05","cited_by_count":4,"area":null},{"id":"2205.00693","title":"Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding","created":"2022-05-02","cited_by_count":4,"area":null},{"id":"2309.08227","title":"VERSE: Virtual-Gradient Aware Streaming Lifelong Learning with Anytime Inference","created":"2023-09-15","cited_by_count":4,"area":null},{"id":"2310.07838","title":"Towards the Fundamental Limits of Knowledge Transfer over Finite Domains","created":"2023-10-11","cited_by_count":4,"area":null}],"next_cursor":"100"}