{"total":119,"rows":[{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311,"area":null},{"id":"2106.14448","title":"R-Drop: Regularized Dropout for Neural Networks","created":"2021-06-28","cited_by_count":202,"area":null},{"id":"2407.14679","title":"Compact Language Models via Pruning and Knowledge Distillation","created":"2024-07-19","cited_by_count":148,"area":"distill"},{"id":"2204.06986","title":"Cross-Image Relational Knowledge Distillation for Semantic Segmentation","created":"2022-04-14","cited_by_count":118,"area":"distill"},{"id":"2205.01529","title":"Masked Generative Distillation","created":"2022-05-03","cited_by_count":107,"area":"distill"},{"id":"2106.04149","title":"To Smooth or Not? When Label Smoothing Meets Noisy Labels","created":"2021-06-08","cited_by_count":70,"area":null},{"id":"2303.13005","title":"From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels","created":"2023-03-23","cited_by_count":69,"area":"distill"},{"id":"2209.04599","title":"Preserving Privacy in Federated Learning with Ensemble Cross-Domain Knowledge Distillation","created":"2022-09-10","cited_by_count":45,"area":"distill"},{"id":"2309.16286","title":"Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning","created":"2023-09-28","cited_by_count":40,"area":null},{"id":"2308.02117","title":"VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs","created":"2023-08-04","cited_by_count":35,"area":"distill"},{"id":"2209.02432","title":"ViTKD: Practical Guidelines for ViT feature knowledge distillation","created":"2022-09-06","cited_by_count":34,"area":"distill"},{"id":"2406.10485","title":"A Label is Worth a Thousand Images in Dataset Distillation","created":"2024-06-15","cited_by_count":31,"area":null},{"id":"2210.03312","title":"Distillation-Resistant Watermarking for Model Protection in NLP","created":"2022-10-07","cited_by_count":30,"area":"safety"},{"id":"2305.05010","title":"Do Not Blindly Imitate the Teacher: Using Perturbed Loss for Knowledge Distillation","created":"2023-05-08","cited_by_count":25,"area":"distill"},{"id":"2210.04208","title":"Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis","created":"2022-10-09","cited_by_count":24,"area":null},{"id":"2210.04427","title":"Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again","created":"2022-10-10","cited_by_count":23,"area":"distill"},{"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":"2107.01691","title":"Bag of Instances Aggregation Boosts Self-supervised Distillation","created":"2021-07-04","cited_by_count":22,"area":null},{"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":"2203.05180","title":"Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability","created":"2022-03-10","cited_by_count":21,"area":"distill"},{"id":"2301.13304","title":"Understanding Self-Distillation in the Presence of Label Noise","created":"2023-01-30","cited_by_count":21,"area":"distill"},{"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":"2210.12787","title":"Respecting Transfer Gap in Knowledge Distillation","created":"2022-10-23","cited_by_count":18,"area":"distill"},{"id":"2406.03470","title":"SpikeZIP-TF: Conversion is All You Need for Transformer-based SNN","created":"2024-06-05","cited_by_count":18,"area":null},{"id":"2211.09768","title":"D$^3$ETR: Decoder Distillation for Detection Transformer","created":"2022-11-17","cited_by_count":17,"area":"distill"},{"id":"2307.00331","title":"Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision","created":"2023-07-01","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":"2503.16870","title":"Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs","created":"2025-03-21","cited_by_count":16,"area":"distill"},{"id":"2207.01426","title":"Dynamic Contrastive Distillation for Image-Text Retrieval","created":"2022-07-04","cited_by_count":14,"area":null},{"id":"2208.14143","title":"FAKD: Feature Augmented Knowledge Distillation for Semantic Segmentation","created":"2022-08-30","cited_by_count":14,"area":"distill"},{"id":"2308.14084","title":"Practical Edge Detection via Robust Collaborative Learning","created":"2023-08-27","cited_by_count":13,"area":null},{"id":"2109.14960","title":"Prune Your Model Before Distill It","created":"2021-09-30","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":"2305.10893","title":"Student-friendly Knowledge Distillation","created":"2023-05-18","cited_by_count":11,"area":"distill"},{"id":"2310.10429","title":"Exploiting User Comments for Early Detection of Fake News Prior to Users' Commenting","created":"2023-10-16","cited_by_count":11,"area":null},{"id":"2407.09083","title":"BKDSNN: Enhancing the Performance of Learning-based Spiking Neural Networks Training with Blurred Knowledge Distillation","created":"2024-07-12","cited_by_count":11,"area":"distill"},{"id":"2411.12843","title":"Reward Modeling with Ordinal Feedback: Wisdom of the Crowd","created":"2024-11-19","cited_by_count":11,"area":"alignment"},{"id":"2408.15641","title":"MMDRFuse: Distilled Mini-Model with Dynamic Refresh for Multi-Modality Image Fusion","created":"2024-08-28","cited_by_count":10,"area":null},{"id":"2506.14457","title":"Dataset distillation for memorized data: Soft labels can leak held-out teacher knowledge","created":"2025-06-17","cited_by_count":10,"area":null},{"id":"2208.10139","title":"Rethinking Knowledge Distillation via Cross-Entropy","created":"2022-08-22","cited_by_count":9,"area":"distill"},{"id":"2405.14736","title":"GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost","created":"2024-05-23","cited_by_count":9,"area":null},{"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":"2305.19412","title":"Are Large Kernels Better Teachers than Transformers for ConvNets?","created":"2023-05-30","cited_by_count":8,"area":"distill"},{"id":"2312.04168","title":"Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic Segmentation","created":"2023-12-07","cited_by_count":8,"area":"distill"},{"id":"2403.08215","title":"LIX: Implicitly Infusing Spatial Geometric Prior Knowledge into Visual Semantic Segmentation for Autonomous Driving","created":"2024-03-13","cited_by_count":8,"area":"distill"},{"id":"2102.06849","title":"Distilling Double Descent","created":"2021-02-13","cited_by_count":7,"area":"distill"},{"id":"2208.13648","title":"Dynamic Data-Free Knowledge Distillation by Easy-to-Hard Learning Strategy","created":"2022-08-29","cited_by_count":7,"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":"2305.05233","title":"DynamicKD: An Effective Knowledge Distillation via Dynamic Entropy Correction-Based Distillation for Gap Optimizing","created":"2023-05-09","cited_by_count":7,"area":"distill"},{"id":"2411.01547","title":"Decoupling Dark Knowledge via Block-wise Logit Distillation for Feature-level Alignment","created":"2024-11-03","cited_by_count":7,"area":"distill"},{"id":"2112.02747","title":"Making a Bird AI Expert Work for You and Me","created":"2021-12-06","cited_by_count":6,"area":null},{"id":"2205.10986","title":"Boosting Multi-Label Image Classification with Complementary Parallel Self-Distillation","created":"2022-05-23","cited_by_count":6,"area":"distill"},{"id":"2210.02099","title":"Automated Graph Self-supervised Learning via Multi-teacher Knowledge Distillation","created":"2022-10-05","cited_by_count":6,"area":"distill"},{"id":"2303.13212","title":"A Simple and Generic Framework for Feature Distillation via Channel-wise Transformation","created":"2023-03-23","cited_by_count":6,"area":"distill"},{"id":"2404.12711","title":"Dynamic Temperature Knowledge Distillation","created":"2024-04-19","cited_by_count":6,"area":"distill"},{"id":"2404.13322","title":"MergeNet: Knowledge Migration across Heterogeneous Models, Tasks, and Modalities","created":"2024-04-20","cited_by_count":6,"area":null},{"id":"2412.09388","title":"All You Need in Knowledge Distillation Is a Tailored Coordinate System","created":"2024-12-12","cited_by_count":6,"area":"distill"},{"id":"2403.13512","title":"Scale Decoupled Distillation","created":"2024-03-20","cited_by_count":5,"area":"distill"},{"id":"2404.03693","title":"Improve Knowledge Distillation via Label Revision and Data Selection","created":"2024-04-03","cited_by_count":5,"area":"distill"},{"id":"2504.02011","title":"Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression","created":"2025-04-02","cited_by_count":5,"area":"diffusion"},{"id":"2309.02719","title":"DMKD: Improving Feature-based Knowledge Distillation for Object Detection Via Dual Masking Augmentation","created":"2023-09-06","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":"2401.15500","title":"Data-Driven Estimation of the False Positive Rate of the Bayes Binary Classifier via Soft Labels","created":"2024-01-27","cited_by_count":4,"area":null},{"id":"2402.01863","title":"DFML: Decentralized Federated Mutual Learning","created":"2024-02-02","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":"2407.14768","title":"Teach Harder, Learn Poorer: Rethinking Hard Sample Distillation for GNN-to-MLP Knowledge Distillation","created":"2024-07-20","cited_by_count":4,"area":"distill"},{"id":"2409.10362","title":"Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning","created":"2024-09-16","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":"2310.03669","title":"LumiNet: Perception-Driven Knowledge Distillation via Statistical Logit Calibration","created":"2023-10-05","cited_by_count":3,"area":"distill"},{"id":"2312.08700","title":"RdimKD: Generic Distillation Paradigm by Dimensionality Reduction","created":"2023-12-14","cited_by_count":3,"area":"distill"},{"id":"2505.22027","title":"Improving Respiratory Sound Classification with Architecture-Agnostic Knowledge Distillation from Ensembles","created":"2025-05-28","cited_by_count":3,"area":"distill"},{"id":"2506.18999","title":"Diffusion Transformer-to-Mamba Distillation for High-Resolution Image Generation","created":"2025-06-23","cited_by_count":3,"area":"diffusion"},{"id":"2309.09571","title":"Heterogeneous Generative Knowledge Distillation with Masked Image Modeling","created":"2023-09-18","cited_by_count":2,"area":"distill"},{"id":"2310.13321","title":"Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-Augmenting","created":"2023-10-20","cited_by_count":2,"area":null},{"id":"2312.15112","title":"Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge Distillation","created":"2023-12-22","cited_by_count":2,"area":"distill"},{"id":"2402.05305","title":"Knowledge Distillation for Road Detection based on cross-model Semi-Supervised Learning","created":"2024-02-07","cited_by_count":2,"area":"distill"},{"id":"2407.09958","title":"Partner in Crime: Boosting Targeted Poisoning Attacks against Federated Learning","created":"2024-07-13","cited_by_count":2,"area":null},{"id":"2504.07691","title":"Distilling Knowledge from Heterogeneous Architectures for Semantic Segmentation","created":"2025-04-10","cited_by_count":2,"area":"distill"},{"id":"2509.20854","title":"Punching Above Precision: Small Quantized Model Distillation with Learnable Regularizer","created":"2025-09-25","cited_by_count":2,"area":"distill"},{"id":"2603.12270","title":"Task-Specific Knowledge Distillation via Intermediate Probes","created":"2026-02-18","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":"2112.00324","title":"Optimizing for In-memory Deep Learning with Emerging Memory Technology","created":"2021-12-01","cited_by_count":1,"area":null},{"id":"2310.09250","title":"It's an Alignment, Not a Trade-off: Revisiting Bias and Variance in Deep Models","created":"2023-10-13","cited_by_count":1,"area":null},{"id":"2407.12073","title":"Relational Representation Distillation","created":"2024-07-16","cited_by_count":1,"area":"distill"},{"id":"2409.01679","title":"Adaptive Explicit Knowledge Transfer for Knowledge Distillation","created":"2024-09-03","cited_by_count":1,"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":"2410.07857","title":"SNN-PAR: Energy Efficient Pedestrian Attribute Recognition via Spiking Neural Networks","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2501.11712","title":"YouLeQD: Decoding the Cognitive Complexity of Questions and Engagement in Online Educational Videos from Learners' Perspectives","created":"2025-01-20","cited_by_count":1,"area":null},{"id":"2506.04567","title":"StatsMerging: Statistics-Guided Model Merging via Task-Specific Teacher Distillation","created":"2025-06-05","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":"2603.15150","title":"SNCE: Geometry-Aware Supervision for Scalable Discrete Image Generation","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2103.00053","title":"PURSUhInT: In Search of Informative Hint Points Based on Layer Clustering for Knowledge Distillation","created":"2021-02-26","cited_by_count":0,"area":"distill"},{"id":"2108.06681","title":"Multi-granularity for knowledge distillation","created":"2021-08-15","cited_by_count":0,"area":"distill"},{"id":"2301.13444","title":"Rethinking Soft Label in Label Distribution Learning Perspective","created":"2023-01-31","cited_by_count":0,"area":null},{"id":"2304.11004","title":"Knowledge Distillation Under Ideal Joint Classifier Assumption","created":"2023-04-19","cited_by_count":0,"area":"distill"},{"id":"2407.11802","title":"Discriminative and Consistent Representation Distillation","created":"2024-07-16","cited_by_count":0,"area":"distill"},{"id":"2409.02020","title":"Efficient Point Cloud Classification via Offline Distillation Framework and Negative-Weight Self-Distillation Technique","created":"2024-09-03","cited_by_count":0,"area":"distill"}],"next_cursor":"100"}