{"total":89,"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":"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":"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":"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":"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":"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":"2201.06227","title":"Egeria: Efficient DNN Training with Knowledge-Guided Layer Freezing","created":"2022-01-17","cited_by_count":22,"area":null},{"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":"2202.04598","title":"Reproducibility in Optimization: Theoretical Framework and Limits","created":"2022-02-09","cited_by_count":21,"area":null},{"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":"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":"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":"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":"2202.10492","title":"CaMEL: Mean Teacher Learning for Image Captioning","created":"2022-02-21","cited_by_count":14,"area":null},{"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":"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":"2407.02596","title":"Towards More Realistic Extraction Attacks: An Adversarial Perspective","created":"2024-07-02","cited_by_count":8,"area":null},{"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":"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":"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":"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":"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":"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":"2307.04470","title":"Test-Time Adaptation for Nighttime Color-Thermal Semantic Segmentation","created":"2023-07-10","cited_by_count":4,"area":null},{"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":"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":"2506.02964","title":"FORLA: Federated Object-centric Representation Learning with Slot Attention","created":"2025-06-03","cited_by_count":3,"area":null},{"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":"2505.23337","title":"Matryoshka Model Learning for Improved Elastic Student Models","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2507.15256","title":"Optimal Transceiver Design in Over-the-Air Federated Distillation","created":"2025-07-21","cited_by_count":2,"area":null},{"id":"2108.05092","title":"Cooperative Learning for Noisy Supervision","created":"2021-08-11","cited_by_count":1,"area":null},{"id":"2211.10684","title":"Personalized Federated Learning with Hidden Information on Personalized Prior","created":"2022-11-19","cited_by_count":1,"area":null},{"id":"2305.04135","title":"Maintaining Stability and Plasticity for Predictive Churn Reduction","created":"2023-05-06","cited_by_count":1,"area":null},{"id":"2403.09086","title":"Learning from straggler clients in federated learning","created":"2024-03-14","cited_by_count":1,"area":null},{"id":"2408.08250","title":"Computer Vision Model Compression Techniques for Embedded Systems: A Survey","created":"2024-08-15","cited_by_count":1,"area":null},{"id":"2501.00693","title":"Beyond Model Scale Limits: End-Edge-Cloud Federated Learning with Self-Rectified Knowledge Agglomeration","created":"2025-01-01","cited_by_count":1,"area":null},{"id":"2605.13826","title":"Reducing cross-sample prediction churn in scientific machine learning","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2104.00698","title":"Back to Square One: Superhuman Performance in Chutes and Ladders Through Deep Neural Networks and Tree Search","created":"2021-04-01","cited_by_count":0,"area":null},{"id":"2108.12124","title":"Canoe : A System for Collaborative Learning for Neural Nets","created":"2021-08-27","cited_by_count":0,"area":null},{"id":"2110.06435","title":"Dropout Prediction Uncertainty Estimation Using Neuron Activation Strength","created":"2021-10-13","cited_by_count":0,"area":null},{"id":"2307.09177","title":"Intuitive Access to Smartphone Settings Using Relevance Model Trained by Contrastive Learning","created":"2023-07-15","cited_by_count":0,"area":null},{"id":"2312.11555","title":"CR-SFP: Learning Consistent Representation for Soft Filter Pruning","created":"2023-12-17","cited_by_count":0,"area":null},{"id":"2312.11905","title":"Convergence Visualizer of Decentralized Federated Distillation with Reduced Communication Costs","created":"2023-12-19","cited_by_count":0,"area":null},{"id":"2402.05033","title":"Majority Kernels: An Approach to Leverage Big Model Dynamics for Efficient Small Model Training","created":"2024-02-07","cited_by_count":0,"area":null},{"id":"2407.06339","title":"Noise-Free Explanation for Driving Action Prediction","created":"2024-07-08","cited_by_count":0,"area":null},{"id":"2410.07915","title":"A Lightweight Target-Driven Network of Stereo Matching for Inland Waterways","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2509.08225","title":"Ensemble Distribution Distillation for Self-Supervised Human Activity Recognition","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2509.22507","title":"Adaptive Dual-Mode Distillation with Incentive Schemes for Scalable, Heterogeneous Federated Learning on Non-IID Data","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2510.22208","title":"Simplifying Knowledge Transfer in Pretrained Models","created":"2025-10-25","cited_by_count":0,"area":null},{"id":"2604.23268","title":"LatentBurst: A Fast and Efficient Multi Frame Super-Resolution for Hexadeca-Bayer Pattern CIS images","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2605.05718","title":"Enabling Federated Inference via Unsupervised Consensus Embedding","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.09356","title":"Function-Space ADMM for Decentralized Federated Learning: A Control Theoretic Perspective","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2606.24747","title":"Scaling Laws for Task-Specific LLM Distillation","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2608.08525","title":"Out-of-Distribution Federated Distillation with Domain-Aware Proxy","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2610.02856","title":"Adaptive Mutual Distillation for Balanced Multi-Task Post-Training of Large Language Models","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}