{"total":110,"rows":[{"id":"2106.14448","title":"R-Drop: Regularized Dropout for Neural Networks","created":"2021-06-28","cited_by_count":202,"area":null},{"id":"2106.11342","title":"Dive into Deep Learning","created":"2021-06-21","cited_by_count":111,"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":"2202.00661","title":"When Do Flat Minima Optimizers Work?","created":"2022-02-01","cited_by_count":78,"area":null},{"id":"2409.03137","title":"The AdEMAMix Optimizer: Better, Faster, Older","created":"2024-09-05","cited_by_count":54,"area":null},{"id":"2103.01396","title":"DeepReDuce: ReLU Reduction for Fast Private Inference","created":"2021-03-02","cited_by_count":50,"area":null},{"id":"2110.03677","title":"Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect","created":"2021-10-07","cited_by_count":50,"area":null},{"id":"2406.09405","title":"Why Warmup the Learning Rate? Underlying Mechanisms and Improvements","created":"2024-06-13","cited_by_count":46,"area":null},{"id":"2203.14186","title":"RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolution","created":"2022-03-27","cited_by_count":44,"area":null},{"id":"2402.17564","title":"Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers","created":"2024-02-27","cited_by_count":35,"area":null},{"id":"2107.08621","title":"Face.evoLVe: A High-Performance Face Recognition Library","created":"2021-07-19","cited_by_count":26,"area":null},{"id":"2306.17833","title":"Resetting the Optimizer in Deep RL: An Empirical Study","created":"2023-06-30","cited_by_count":26,"area":null},{"id":"2507.20016","title":"FedSWA: Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging","created":"2025-07-26","cited_by_count":25,"area":null},{"id":"2202.04777","title":"Exact Solutions of a Deep Linear Network","created":"2022-02-10","cited_by_count":24,"area":null},{"id":"2410.23782","title":"Video Token Merging for Long-form Video Understanding","created":"2024-10-31","cited_by_count":23,"area":"inference"},{"id":"2507.17634","title":"WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training","created":"2025-07-23","cited_by_count":23,"area":null},{"id":"2410.23922","title":"Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training","created":"2024-10-31","cited_by_count":22,"area":null},{"id":"2105.03588","title":"Facial Emotion Recognition: State of the Art Performance on FER2013","created":"2021-05-08","cited_by_count":20,"area":null},{"id":"2112.02805","title":"Forward Compatible Training for Large-Scale Embedding Retrieval Systems","created":"2021-12-06","cited_by_count":19,"area":null},{"id":"2205.14375","title":"WaveMix: A Resource-efficient Neural Network for Image Analysis","created":"2022-05-28","cited_by_count":19,"area":null},{"id":"2308.06749","title":"FastLLVE: Real-Time Low-Light Video Enhancement with Intensity-Aware Lookup Table","created":"2023-08-13","cited_by_count":16,"area":null},{"id":"2407.19325","title":"Investigating Critical Period Effects in Language Acquisition through Neural Language Models","created":"2024-07-27","cited_by_count":16,"area":null},{"id":"2110.14109","title":"Eigencurve: Optimal Learning Rate Schedule for SGD on Quadratic Objectives with Skewed Hessian Spectrums","created":"2021-10-27","cited_by_count":15,"area":null},{"id":"2105.10762","title":"AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly","created":"2021-05-22","cited_by_count":14,"area":null},{"id":"2110.01606","title":"Breast Cancer Diagnosis in Two-View Mammography Using End-to-End Trained EfficientNet-Based Convolutional Network","created":"2021-10-01","cited_by_count":13,"area":null},{"id":"2309.13425","title":"MiliPoint: A Point Cloud Dataset for mmWave Radar","created":"2023-09-23","cited_by_count":13,"area":null},{"id":"2310.02000","title":"MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts","created":"2023-10-03","cited_by_count":13,"area":null},{"id":"2104.05215","title":"SCPM-Net: An Anchor-free 3D Lung Nodule Detection Network using Sphere Representation and Center Points Matching","created":"2021-04-12","cited_by_count":12,"area":null},{"id":"2109.15068","title":"iShape: A First Step Towards Irregular Shape Instance Segmentation","created":"2021-09-30","cited_by_count":12,"area":null},{"id":"2205.01915","title":"Generalized Knowledge Distillation via Relationship Matching","created":"2022-05-04","cited_by_count":12,"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":"2409.08770","title":"Increasing Both Batch Size and Learning Rate Accelerates Stochastic Gradient Descent","created":"2024-09-13","cited_by_count":11,"area":null},{"id":"2202.07184","title":"On the Origins of the Block Structure Phenomenon in Neural Network Representations","created":"2022-02-15","cited_by_count":10,"area":null},{"id":"2203.03689","title":"WaveMix: Resource-efficient Token Mixing for Images","created":"2022-03-07","cited_by_count":9,"area":null},{"id":"2205.09180","title":"Learning Rate Curriculum","created":"2022-05-18","cited_by_count":9,"area":null},{"id":"2407.05385","title":"Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis","created":"2024-07-07","cited_by_count":9,"area":null},{"id":"2204.03475","title":"Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results","created":"2022-04-07","cited_by_count":8,"area":null},{"id":"2301.12985","title":"Integrating Earth Observation Data into Causal Inference: Challenges and Opportunities","created":"2023-01-30","cited_by_count":8,"area":null},{"id":"2306.14522","title":"Nonconvex Stochastic Bregman Proximal Gradient Method with Application to Deep Learning","created":"2023-06-26","cited_by_count":7,"area":null},{"id":"2201.08017","title":"Fine-Grained Trajectory-based Travel Time Estimation for Multi-city Scenarios Based on Deep Meta-Learning","created":"2022-01-20","cited_by_count":6,"area":null},{"id":"2205.11416","title":"The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains","created":"2022-05-23","cited_by_count":6,"area":null},{"id":"2303.11909","title":"The Multiscale Surface Vision Transformer","created":"2023-03-21","cited_by_count":6,"area":null},{"id":"2411.09126","title":"SCAN: Bootstrapping Contrastive Pre-training for Data Efficiency","created":"2024-11-14","cited_by_count":6,"area":null},{"id":"2111.08274","title":"HADFL: Heterogeneity-aware Decentralized Federated Learning Framework","created":"2021-11-16","cited_by_count":5,"area":null},{"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":"2309.14053","title":"Revisiting LARS for Large Batch Training Generalization of Neural Networks","created":"2023-09-25","cited_by_count":5,"area":null},{"id":"2602.05813","title":"Where Does Warm-Up Come From? Adaptive Scheduling for Norm-Constrained Optimizers","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2110.00959","title":"Boost Neural Networks by Checkpoints","created":"2021-10-03","cited_by_count":4,"area":null},{"id":"2202.04509","title":"Optimal learning rate schedules in high-dimensional non-convex optimization problems","created":"2022-02-09","cited_by_count":4,"area":null},{"id":"2204.06240","title":"CowClip: Reducing CTR Prediction Model Training Time from 12 hours to 10 minutes on 1 GPU","created":"2022-04-13","cited_by_count":4,"area":null},{"id":"2206.06410","title":"Estimating Causal Effects Under Image Confounding Bias with an Application to Poverty in Africa","created":"2022-06-13","cited_by_count":4,"area":null},{"id":"2211.00269","title":"Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks","created":"2022-11-01","cited_by_count":4,"area":null},{"id":"2303.01777","title":"Benchmarking White Blood Cell Classification Under Domain Shift","created":"2023-03-03","cited_by_count":4,"area":null},{"id":"2401.08505","title":"Harnessing Orthogonality to Train Low-Rank Neural Networks","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2404.16882","title":"ThermoPore: Predicting Part Porosity Based on Thermal Images Using Deep Learning","created":"2024-04-23","cited_by_count":4,"area":null},{"id":"2409.10362","title":"Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning","created":"2024-09-16","cited_by_count":4,"area":"distill"},{"id":"2509.07972","title":"Theoretical Analysis on how Learning Rate Warmup Accelerates Convergence","created":"2025-09-09","cited_by_count":4,"area":null},{"id":"2303.12892","title":"Improving Transformer Performance for French Clinical Notes Classification Using Mixture of Experts on a Limited Dataset","created":"2023-03-22","cited_by_count":3,"area":"moe"},{"id":"2304.04664","title":"Inductive biases in deep learning models for weather prediction","created":"2023-04-06","cited_by_count":3,"area":null},{"id":"2306.11309","title":"Multi-pass Training and Cross-information Fusion for Low-resource End-to-end Accented Speech Recognition","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2311.15051","title":"Gradient Descent with Polyak's Momentum Finds Flatter Minima via Large Catapults","created":"2023-11-25","cited_by_count":3,"area":null},{"id":"2412.10002","title":"NowYouSee Me: Context-Aware Automatic Audio Description","created":"2024-12-13","cited_by_count":3,"area":null},{"id":"2509.21006","title":"AnywhereVLA: Language-Conditioned Exploration and Mobile Manipulation","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2606.25971","title":"Improving Neural Network Training by Decoupling the Magnitude and Direction of Weight Vectors","created":"2026-06-24","cited_by_count":3,"area":"moe"},{"id":"2103.01717","title":"Transportation Density Reduction Caused by City Lockdowns Across the World during the COVID-19 Epidemic: From the View of High-resolution Remote Sensing Imagery","created":"2021-03-02","cited_by_count":2,"area":null},{"id":"2105.10633","title":"Revisiting Knowledge Distillation for Object Detection","created":"2021-05-22","cited_by_count":2,"area":"distill"},{"id":"2202.12549","title":"Raman Spectrum Matching with Contrastive Representation Learning","created":"2022-02-25","cited_by_count":2,"area":null},{"id":"2205.10456","title":"PSO-Convolutional Neural Networks with Heterogeneous Learning Rate","created":"2022-05-20","cited_by_count":2,"area":null},{"id":"2301.05993","title":"Empirical study of the modulus as activation function in computer vision applications","created":"2023-01-15","cited_by_count":2,"area":null},{"id":"2302.07455","title":"A lightweight network for photovoltaic cell defect detection in electroluminescence images based on neural architecture search and knowledge distillation","created":"2023-02-15","cited_by_count":2,"area":null},{"id":"2305.13644","title":"Physics-Assisted Reduced-Order Modeling for Identifying Dominant Features of Transonic Buffet","created":"2023-05-23","cited_by_count":2,"area":null},{"id":"2306.05108","title":"Hybrid Graph: A Unified Graph Representation with Datasets and Benchmarks for Complex Graphs","created":"2023-06-08","cited_by_count":2,"area":null},{"id":"2306.05143","title":"Genomic Interpreter: A Hierarchical Genomic Deep Neural Network with 1D Shifted Window Transformer","created":"2023-06-08","cited_by_count":2,"area":null},{"id":"2311.08745","title":"Using Stochastic Gradient Descent to Smooth Nonconvex Functions: Analysis of Implicit Graduated Optimization","created":"2023-11-15","cited_by_count":2,"area":null},{"id":"2403.04125","title":"ComFe: An Interpretable Head for Vision Transformers","created":"2024-03-07","cited_by_count":2,"area":null},{"id":"2405.17377","title":"How Do the Architecture and Optimizer Affect Representation Learning? On the Training Dynamics of Representations in Deep Neural Networks","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2503.03783","title":"Passive Heart Rate Monitoring During Smartphone Use in Everyday Life","created":"2025-03-04","cited_by_count":2,"area":null},{"id":"2503.23190","title":"Ethereum Price Prediction Employing Large Language Models for Short-term and Few-shot Forecasting","created":"2025-03-29","cited_by_count":2,"area":null},{"id":"2511.06172","title":"MambaOVSR: Multiscale Fusion with Global Motion Modeling for Chinese Opera Video Super-Resolution","created":"2025-11-09","cited_by_count":2,"area":"ssm"},{"id":"2601.20064","title":"DiSa: Saliency-Aware Foreground-Background Disentangled Framework for Open-Vocabulary Semantic Segmentation","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2102.03002","title":"Zero Training Overhead Portfolios for Learning to Solve Combinatorial Problems","created":"2021-02-05","cited_by_count":1,"area":null},{"id":"2301.06178","title":"Bike Frames: Understanding the Implicit Portrayal of Cyclists in the News","created":"2023-01-15","cited_by_count":1,"area":null},{"id":"2309.15608","title":"NoSENSE: Learned unrolled cardiac MRI reconstruction without explicit sensitivity maps","created":"2023-09-27","cited_by_count":1,"area":null},{"id":"2401.08830","title":"Stochastic Subnetwork Annealing: A Regularization Technique for Fine Tuning Pruned Subnetworks","created":"2024-01-16","cited_by_count":1,"area":null},{"id":"2401.17542","title":"A Medical Data-Effective Learning Benchmark for Highly Efficient Pre-training of Foundation Models","created":"2024-01-31","cited_by_count":1,"area":null},{"id":"2405.07031","title":"Global Motion Understanding in Large-Scale Video Object Segmentation","created":"2024-05-11","cited_by_count":1,"area":null},{"id":"2405.12174","title":"CT-Eval: Benchmarking Chinese Text-to-Table Performance in Large Language Models","created":"2024-05-20","cited_by_count":1,"area":null},{"id":"2510.02670","title":"Topological Invariance and Breakdown in Learning","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2605.24451","title":"Phonetic Modeling of Dialectal Variation in Vietnamese Speech","created":"2026-05-23","cited_by_count":1,"area":null},{"id":"2605.29547","title":"Singularity-aware Optimization via Randomized Geometric Probing: Towards Stable Non-smooth Optimization","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2203.03886","title":"Boosting Mask R-CNN Performance for Long, Thin Forensic Traces with Pre-Segmentation and IoU Region Merging","created":"2022-03-08","cited_by_count":0,"area":null},{"id":"2203.08694","title":"Turning Stocks into Memes: A Dataset for Understanding How Social Communities Can Drive Wall Street","created":"2022-03-16","cited_by_count":0,"area":null},{"id":"2212.07836","title":"Spatially-resolved Thermometry from Line-of-Sight Emission Spectroscopy via Machine Learning","created":"2022-12-15","cited_by_count":0,"area":null},{"id":"2303.00356","title":"A Deep Reinforcement Learning Trader without Offline Training","created":"2023-03-01","cited_by_count":0,"area":null},{"id":"2305.03919","title":"DBAT: Dynamic Backward Attention Transformer for Material Segmentation with Cross-Resolution Patches","created":"2023-05-06","cited_by_count":0,"area":null},{"id":"2311.12430","title":"AR Visualization System for Ship Detection and Recognition Based on AI","created":"2023-11-21","cited_by_count":0,"area":null},{"id":"2311.15846","title":"Learning with Noisy Low-Cost MOS for Image Quality Assessment via Dual-Bias Calibration","created":"2023-11-27","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":"2402.05067","title":"A Novel Paradigm in Solving Multiscale Problems","created":"2024-02-07","cited_by_count":0,"area":null},{"id":"2402.13033","title":"Enhancing Node Representations for Real-World Complex Networks with Topological Augmentation","created":"2024-02-20","cited_by_count":0,"area":null}],"next_cursor":"100"}