{"total":146,"rows":[{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968,"area":null},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824,"area":null},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619,"area":null},{"id":"2206.07137","title":"Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt","created":"2022-06-14","cited_by_count":236,"area":null},{"id":"2111.00643","title":"Learning Distilled Collaboration Graph for Multi-Agent Perception","created":"2021-11-01","cited_by_count":194,"area":"distill"},{"id":"2108.13323","title":"FedKD: Communication Efficient Federated Learning via Knowledge Distillation","created":"2021-08-30","cited_by_count":187,"area":"distill"},{"id":"2211.08413","title":"Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges","created":"2022-11-15","cited_by_count":138,"area":null},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"area":null},{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118,"area":null},{"id":"2103.14475","title":"Distilling Object Detectors via Decoupled Features","created":"2021-03-26","cited_by_count":106,"area":"distill"},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2102.02514","title":"FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learning","created":"2021-02-04","cited_by_count":69,"area":null},{"id":"2109.11369","title":"Recent Advances of Continual Learning in Computer Vision: An Overview","created":"2021-09-23","cited_by_count":55,"area":null},{"id":"2203.14956","title":"LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection","created":"2022-03-28","cited_by_count":55,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2305.13803","title":"NORM: Knowledge Distillation via N-to-One Representation Matching","created":"2023-05-23","cited_by_count":44,"area":"distill"},{"id":"2209.05310","title":"On the Factory Floor: ML Engineering for Industrial-Scale Ads Recommendation Models","created":"2022-09-12","cited_by_count":34,"area":null},{"id":"2307.12574","title":"A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation","created":"2023-07-24","cited_by_count":33,"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":"2211.04742","title":"Knowledge Distillation for Federated Learning: a Practical Guide","created":"2022-11-09","cited_by_count":31,"area":"distill"},{"id":"2103.13811","title":"Student Network Learning via Evolutionary Knowledge Distillation","created":"2021-03-23","cited_by_count":30,"area":"distill"},{"id":"2102.03349","title":"On the Reproducibility of Neural Network Predictions","created":"2021-02-05","cited_by_count":29,"area":null},{"id":"2105.00623","title":"Black-Box Dissector: Towards Erasing-based Hard-Label Model Stealing Attack","created":"2021-05-03","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":"2108.06908","title":"Online Multi-Granularity Distillation for GAN Compression","created":"2021-08-16","cited_by_count":24,"area":null},{"id":"2203.14666","title":"Federated Learning with Position-Aware Neurons","created":"2022-03-28","cited_by_count":24,"area":null},{"id":"2109.08119","title":"Personalized Federated Learning for Heterogeneous Clients with Clustered Knowledge Transfer","created":"2021-09-16","cited_by_count":23,"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":"2107.02681","title":"VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer","created":"2021-07-06","cited_by_count":22,"area":"distill"},{"id":"2201.06227","title":"Egeria: Efficient DNN Training with Knowledge-Guided Layer Freezing","created":"2022-01-17","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":"2204.07028","title":"Exploring the Distributed Knowledge Congruence in Proxy-data-free Federated Distillation","created":"2022-04-14","cited_by_count":22,"area":null},{"id":"2106.10494","title":"Teacher's pet: understanding and mitigating biases in distillation","created":"2021-06-19","cited_by_count":21,"area":"distill"},{"id":"2202.04598","title":"Reproducibility in Optimization: Theoretical Framework and Limits","created":"2022-02-09","cited_by_count":21,"area":null},{"id":"2302.12156","title":"Personalized Decentralized Federated Learning with Knowledge Distillation","created":"2023-02-23","cited_by_count":21,"area":"distill"},{"id":"2112.03603","title":"Handwritten Mathematical Expression Recognition via Attention Aggregation based Bi-directional Mutual Learning","created":"2021-12-07","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":"2312.00600","title":"Improving Plasticity in Online Continual Learning via Collaborative Learning","created":"2023-12-01","cited_by_count":20,"area":null},{"id":"2210.11948","title":"lo-fi: distributed fine-tuning without communication","created":"2022-10-19","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":"2108.13873","title":"Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs","created":"2021-08-29","cited_by_count":18,"area":null},{"id":"2104.00352","title":"Decentralized and Model-Free Federated Learning: Consensus-Based Distillation in Function Space","created":"2021-04-01","cited_by_count":17,"area":null},{"id":"2106.02654","title":"Churn Reduction via Distillation","created":"2021-06-04","cited_by_count":17,"area":null},{"id":"2301.00389","title":"FedICT: Federated Multi-task Distillation for Multi-access Edge Computing","created":"2023-01-01","cited_by_count":17,"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":"2402.07745","title":"Predictive Churn with the Set of Good Models","created":"2024-02-12","cited_by_count":15,"area":null},{"id":"2410.14635","title":"GenEOL: Harnessing the Generative Power of LLMs for Training-Free Sentence Embeddings","created":"2024-10-18","cited_by_count":15,"area":null},{"id":"2603.02604","title":"Heterogeneous Agent Collaborative Reinforcement Learning","created":"2026-03-03","cited_by_count":15,"area":"agents"},{"id":"2202.10492","title":"CaMEL: Mean Teacher Learning for Image Captioning","created":"2022-02-21","cited_by_count":14,"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":"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":"2312.11489","title":"Agglomerative Federated Learning: Empowering Larger Model Training via End-Edge-Cloud Collaboration","created":"2023-12-01","cited_by_count":10,"area":null},{"id":"2102.10696","title":"Synthesizing Irreproducibility in Deep Networks","created":"2021-02-21","cited_by_count":9,"area":null},{"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":"2211.12881","title":"DGEKT: A Dual Graph Ensemble Learning Method for Knowledge Tracing","created":"2022-11-23","cited_by_count":9,"area":"distill"},{"id":"2101.02375","title":"Dual-Teacher++: Exploiting Intra-domain and Inter-domain Knowledge with Reliable Transfer for Cardiac Segmentation","created":"2021-01-07","cited_by_count":8,"area":null},{"id":"2212.04884","title":"Co-training $2^L$ Submodels for Visual Recognition","created":"2022-12-09","cited_by_count":8,"area":"distill"},{"id":"2407.02596","title":"Towards More Realistic Extraction Attacks: An Adversarial Perspective","created":"2024-07-02","cited_by_count":8,"area":null},{"id":"2409.12111","title":"Applications of Knowledge Distillation in Remote Sensing: A Survey","created":"2024-09-18","cited_by_count":8,"area":"distill"},{"id":"2504.19101","title":"Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generation","created":"2025-04-27","cited_by_count":8,"area":"rag"},{"id":"2102.05140","title":"Locally Adaptive Label Smoothing for Predictive Churn","created":"2021-02-09","cited_by_count":7,"area":null},{"id":"2106.08960","title":"Collaborative Training of Acoustic Encoders for Speech Recognition","created":"2021-06-16","cited_by_count":7,"area":null},{"id":"2204.11660","title":"A Survey on Word Meta-Embedding Learning","created":"2022-04-25","cited_by_count":7,"area":null},{"id":"2310.04830","title":"Extract-Transform-Load for Video Streams","created":"2023-10-07","cited_by_count":7,"area":null},{"id":"2401.04305","title":"Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions","created":"2024-01-09","cited_by_count":7,"area":null},{"id":"2103.11083","title":"Compacting Deep Neural Networks for Internet of Things: Methods and Applications","created":"2021-03-20","cited_by_count":6,"area":null},{"id":"2204.04735","title":"Reducing Model Jitter: Stable Re-training of Semantic Parsers in Production Environments","created":"2022-04-10","cited_by_count":6,"area":null},{"id":"2205.11440","title":"Federated Distillation based Indoor Localization for IoT Networks","created":"2022-05-23","cited_by_count":6,"area":null},{"id":"2206.06479","title":"Robust Distillation for Worst-class Performance","created":"2022-06-13","cited_by_count":6,"area":"distill"},{"id":"2210.05657","title":"The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes","created":"2022-10-11","cited_by_count":6,"area":null},{"id":"2306.00169","title":"Inconsistency, Instability, and Generalization Gap of Deep Neural Network Training","created":"2023-05-31","cited_by_count":6,"area":null},{"id":"2403.14001","title":"Evaluating Unsupervised Dimensionality Reduction Methods for Pretrained Sentence Embeddings","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2405.04342","title":"The Curse of Diversity in Ensemble-Based Exploration","created":"2024-05-07","cited_by_count":6,"area":"deeprl"},{"id":"2406.17989","title":"Learning Neural Networks with Sparse Activations","created":"2024-06-26","cited_by_count":6,"area":null},{"id":"2103.01435","title":"Improved Techniques for Quantizing Deep Networks with Adaptive Bit-Widths","created":"2021-03-02","cited_by_count":5,"area":null},{"id":"2108.01216","title":"DarkGAN: Exploiting Knowledge Distillation for Comprehensible Audio Synthesis with GANs","created":"2021-08-03","cited_by_count":5,"area":"distill"},{"id":"2111.14347","title":"Efficient Federated Learning for AIoT Applications Using Knowledge Distillation","created":"2021-11-29","cited_by_count":5,"area":"distill"},{"id":"2203.15837","title":"Learning to Collide: Recommendation System Model Compression with Learned Hash Functions","created":"2022-03-28","cited_by_count":5,"area":null},{"id":"2205.02468","title":"Alignahead: Online Cross-Layer Knowledge Extraction on Graph Neural Networks","created":"2022-05-05","cited_by_count":5,"area":"distill"},{"id":"2207.06667","title":"Large-scale Knowledge Distillation with Elastic Heterogeneous Computing Resources","created":"2022-07-14","cited_by_count":5,"area":"distill"},{"id":"2207.14757","title":"ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval","created":"2022-07-29","cited_by_count":5,"area":null},{"id":"2301.05849","title":"Knowledge Distillation in Federated Edge Learning: A Survey","created":"2023-01-14","cited_by_count":5,"area":"distill"},{"id":"2311.08479","title":"Leveraging Foundation Models to Improve Lightweight Clients in Federated Learning","created":"2023-11-14","cited_by_count":5,"area":null},{"id":"2107.12147","title":"Federated Action Recognition on Heterogeneous Embedded Devices","created":"2021-07-18","cited_by_count":4,"area":null},{"id":"2203.05984","title":"Deep Class Incremental Learning from Decentralized Data","created":"2022-03-11","cited_by_count":4,"area":"distill"},{"id":"2307.04470","title":"Test-Time Adaptation for Nighttime Color-Thermal Semantic Segmentation","created":"2023-07-10","cited_by_count":4,"area":null},{"id":"2401.00622","title":"Federated Class-Incremental Learning with New-Class Augmented Self-Distillation","created":"2024-01-01","cited_by_count":4,"area":"distill"},{"id":"2511.15833","title":"EfficientSAM3: Progressive Hierarchical Distillation for Video Concept Segmentation from SAM1, 2, and 3","created":"2025-11-19","cited_by_count":4,"area":null},{"id":"2211.10943","title":"Scalable Collaborative Learning via Representation Sharing","created":"2022-11-20","cited_by_count":3,"area":"distill"},{"id":"2311.09773","title":"To be or not to be? an exploration of continuously controllable prompt engineering","created":"2023-11-16","cited_by_count":3,"area":null},{"id":"2404.13097","title":"DISC: Latent Diffusion Models with Self-Distillation from Separated Conditions for Prostate Cancer Grading","created":"2024-04-19","cited_by_count":3,"area":"diffusion"},{"id":"2506.02964","title":"FORLA: Federated Object-centric Representation Learning with Slot Attention","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2507.00012","title":"Towards Undistillable Models by Minimizing Conditional Mutual Information","created":"2025-06-13","cited_by_count":3,"area":"distill"},{"id":"2511.08322","title":"Mitigating Negative Flips via Margin Preserving Training","created":"2025-11-11","cited_by_count":3,"area":null},{"id":"2103.17008","title":"Collaborative Label Correction via Entropy Thresholding","created":"2021-03-31","cited_by_count":2,"area":null},{"id":"2202.06499","title":"Real World Large Scale Recommendation Systems Reproducibility and Smooth Activations","created":"2022-02-14","cited_by_count":2,"area":null},{"id":"2203.04314","title":"PyNET-QxQ: An Efficient PyNET Variant for QxQ Bayer Pattern Demosaicing in CMOS Image Sensors","created":"2022-03-08","cited_by_count":2,"area":null},{"id":"2206.14868","title":"Teach me how to Interpolate a Myriad of Embeddings","created":"2022-06-29","cited_by_count":2,"area":null},{"id":"2310.06603","title":"V2X-AHD:Vehicle-to-Everything Cooperation Perception via Asymmetric Heterogenous Distillation Network","created":"2023-10-10","cited_by_count":2,"area":null},{"id":"2402.14922","title":"Practical Insights into Knowledge Distillation for Pre-Trained Models","created":"2024-02-22","cited_by_count":2,"area":"distill"}],"next_cursor":"100"}