{"total":78,"rows":[{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446,"area":null},{"id":"2101.05278","title":"GAN Inversion: A Survey","created":"2021-01-14","cited_by_count":367,"area":null},{"id":"2110.13903","title":"NeRV: Neural Representations for Videos","created":"2021-10-26","cited_by_count":256,"area":null},{"id":"2109.14545","title":"Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark","created":"2021-09-29","cited_by_count":155,"area":null},{"id":"2303.07507","title":"Loss of Plasticity in Continual Deep Reinforcement Learning","created":"2023-03-13","cited_by_count":121,"area":null},{"id":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"area":null},{"id":"2308.11958","title":"Maintaining Plasticity in Continual Learning via Regenerative Regularization","created":"2023-08-23","cited_by_count":65,"area":null},{"id":"2306.10711","title":"PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning","created":"2023-06-19","cited_by_count":42,"area":null},{"id":"2103.01649","title":"Learning with Hyperspherical Uniformity","created":"2021-03-02","cited_by_count":35,"area":null},{"id":"2406.06811","title":"Learning Continually by Spectral Regularization","created":"2024-06-10","cited_by_count":34,"area":null},{"id":"2205.11775","title":"Constrained Monotonic Neural Networks","created":"2022-05-24","cited_by_count":32,"area":null},{"id":"2209.02681","title":"How important are activation functions in regression and classification? A survey, performance comparison, and future directions","created":"2022-09-06","cited_by_count":29,"area":null},{"id":"2310.07418","title":"Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages","created":"2023-10-11","cited_by_count":28,"area":null},{"id":"2312.00246","title":"Directions of Curvature as an Explanation for Loss of Plasticity","created":"2023-11-30","cited_by_count":26,"area":null},{"id":"2102.09407","title":"Adaptive Rational Activations to Boost Deep Reinforcement Learning","created":"2021-02-18","cited_by_count":23,"area":null},{"id":"2205.02321","title":"Most Activation Functions Can Win the Lottery Without Excessive Depth","created":"2022-05-04","cited_by_count":21,"area":null},{"id":"2206.08615","title":"On the Number of Regions of Piecewise Linear Neural Networks","created":"2022-06-17","cited_by_count":21,"area":null},{"id":"2102.02694","title":"Invertible DenseNets with Concatenated LipSwish","created":"2021-02-04","cited_by_count":17,"area":null},{"id":"2108.05623","title":"Existence, Stability and Scalability of Orthogonal Convolutional Neural Networks","created":"2021-08-12","cited_by_count":16,"area":null},{"id":"2107.12342","title":"Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learning","created":"2021-07-26","cited_by_count":14,"area":null},{"id":"2410.20634","title":"Plastic Learning with Deep Fourier Features","created":"2024-10-27","cited_by_count":14,"area":null},{"id":"2202.06281","title":"Graph-adaptive Rectified Linear Unit for Graph Neural Networks","created":"2022-02-13","cited_by_count":12,"area":null},{"id":"2201.06714","title":"AdaTerm: Adaptive T-Distribution Estimated Robust Moments for Noise-Robust Stochastic Gradient Optimization","created":"2022-01-18","cited_by_count":11,"area":null},{"id":"2310.07235","title":"Are GATs Out of Balance?","created":"2023-10-11","cited_by_count":10,"area":null},{"id":"2206.09149","title":"Piecewise Linear Neural Networks and Deep Learning","created":"2022-06-18","cited_by_count":7,"area":null},{"id":"2410.23495","title":"DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity","created":"2024-10-30","cited_by_count":7,"area":null},{"id":"2203.04516","title":"Update Compression for Deep Neural Networks on the Edge","created":"2022-03-09","cited_by_count":6,"area":null},{"id":"2203.10502","title":"Adversarial Parameter Attack on Deep Neural Networks","created":"2022-03-20","cited_by_count":6,"area":null},{"id":"2301.09245","title":"Towards NeuroAI: Introducing Neuronal Diversity into Artificial Neural Networks","created":"2023-01-23","cited_by_count":6,"area":null},{"id":"2509.22335","title":"Spectral Collapse Drives Loss of Plasticity in Deep Continual Learning","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2509.22562","title":"Activation Function Design Sustains Plasticity in Continual Learning","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2110.05283","title":"Phase Collapse in Neural Networks","created":"2021-10-11","cited_by_count":5,"area":null},{"id":"2111.00687","title":"RMNet: Equivalently Removing Residual Connection from Networks","created":"2021-11-01","cited_by_count":5,"area":null},{"id":"2210.05436","title":"Retinex Image Enhancement Based on Sequential Decomposition With a Plug-and-Play Framework","created":"2022-10-11","cited_by_count":5,"area":null},{"id":"2301.06132","title":"Deep Diversity-Enhanced Feature Representation of Hyperspectral Images","created":"2023-01-15","cited_by_count":5,"area":null},{"id":"2111.13858","title":"Why KDAC? A general activation function for knowledge discovery","created":"2021-11-27","cited_by_count":4,"area":null},{"id":"2209.06322","title":"FaceTopoNet: Facial Expression Recognition using Face Topology Learning","created":"2022-09-13","cited_by_count":4,"area":null},{"id":"2301.00924","title":"Increasing biases can be more efficient than increasing weights","created":"2023-01-03","cited_by_count":4,"area":null},{"id":"2503.20018","title":"Experience Replay Addresses Loss of Plasticity in Continual Learning","created":"2025-03-25","cited_by_count":4,"area":null},{"id":"2110.11400","title":"Channel redundancy and overlap in convolutional neural networks with channel-wise NNK graphs","created":"2021-10-18","cited_by_count":3,"area":null},{"id":"2201.12795","title":"Training Thinner and Deeper Neural Networks: Jumpstart Regularization","created":"2022-01-30","cited_by_count":3,"area":null},{"id":"2202.03874","title":"Combining Intra-Risk and Contagion Risk for Enterprise Bankruptcy Prediction Using Graph Neural Networks","created":"2022-02-01","cited_by_count":3,"area":null},{"id":"2210.12818","title":"Pushing the Efficiency Limit Using Structured Sparse Convolutions","created":"2022-10-23","cited_by_count":3,"area":null},{"id":"2301.05440","title":"Learnable Heterogeneous Convolution: Learning both topology and strength","created":"2023-01-13","cited_by_count":3,"area":null},{"id":"2305.18483","title":"Bringing regularized optimal transport to lightspeed: a splitting method adapted for GPUs","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2106.07026","title":"Reborn Mechanism: Rethinking the Negative Phase Information Flow in Convolutional Neural Network","created":"2021-06-13","cited_by_count":2,"area":null},{"id":"2107.06405","title":"Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks","created":"2021-07-13","cited_by_count":2,"area":null},{"id":"2110.13732","title":"Improving the efficacy of Deep Learning models for Heart Beat detection on heterogeneous datasets","created":"2021-10-26","cited_by_count":2,"area":null},{"id":"2112.00913","title":"CDLNet: Noise-Adaptive Convolutional Dictionary Learning Network for Blind Denoising and Demosaicing","created":"2021-12-02","cited_by_count":2,"area":null},{"id":"2303.04614","title":"Densely Connected $G$-invariant Deep Neural Networks with Signed Permutation Representations","created":"2023-03-08","cited_by_count":2,"area":null},{"id":"2306.10536","title":"Learn to Enhance the Negative Information in Convolutional Neural Network","created":"2023-06-18","cited_by_count":2,"area":null},{"id":"2402.08236","title":"BERT4FCA: A Method for Bipartite Link Prediction using Formal Concept Analysis and BERT","created":"2024-02-13","cited_by_count":2,"area":null},{"id":"2403.06470","title":"3D-aware Image Generation and Editing with Multi-modal Conditions","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2103.12499","title":"Initializing ReLU networks in an expressive subspace of weights","created":"2021-03-23","cited_by_count":1,"area":null},{"id":"2104.05527","title":"A-FMI: Learning Attributions from Deep Networks via Feature Map Importance","created":"2021-04-12","cited_by_count":1,"area":null},{"id":"2108.00700","title":"Piecewise Linear Units Improve Deep Neural Networks","created":"2021-08-02","cited_by_count":1,"area":null},{"id":"2204.01640","title":"APP: Anytime Progressive Pruning","created":"2022-04-04","cited_by_count":1,"area":null},{"id":"2309.04502","title":"On the Efficacy of Multi-scale Data Samplers for Vision Applications","created":"2023-09-08","cited_by_count":1,"area":null},{"id":"2310.17404","title":"Invariance Measures for Neural Networks","created":"2023-10-26","cited_by_count":1,"area":null},{"id":"2401.03722","title":"From Data to Insights: A Comprehensive Survey on Advanced Applications in Thyroid Cancer Research","created":"2024-01-08","cited_by_count":1,"area":null},{"id":"2401.07272","title":"City Scene Super-Resolution via Geometric Error Minimization","created":"2024-01-14","cited_by_count":1,"area":null},{"id":"2404.19112","title":"Hidden Synergy: $L_1$ Weight Normalization and 1-Path-Norm Regularization","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2504.15051","title":"VeLU: Variance-enhanced Learning Unit for Deep Neural Networks","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2509.19698","title":"A Unified Noise-Curvature View of Loss of Trainability","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2511.05131","title":"DL101 Neural Network Outputs and Loss Functions","created":"2025-11-07","cited_by_count":1,"area":null},{"id":"2605.27673","title":"When do complex-valued neural networks help? A study of representation, geometry, and optimization","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2104.09263","title":"Fitbeat: COVID-19 Estimation based on Wristband Heart Rate","created":"2021-04-19","cited_by_count":0,"area":null},{"id":"2109.07957","title":"Real Time Monocular Vehicle Velocity Estimation using Synthetic Data","created":"2021-09-16","cited_by_count":0,"area":null},{"id":"2111.14349","title":"First Power Linear Unit with Sign","created":"2021-11-29","cited_by_count":0,"area":null},{"id":"2202.12065","title":"Activation Functions: Dive into an optimal activation function","created":"2022-02-24","cited_by_count":0,"area":null},{"id":"2203.12145","title":"Out of Distribution Detection, Generalization, and Robustness Triangle with Maximum Probability Theorem","created":"2022-03-23","cited_by_count":0,"area":null},{"id":"2210.02411","title":"Dynamical Isometry for Residual Networks","created":"2022-10-05","cited_by_count":0,"area":null},{"id":"2305.11077","title":"A Comparative Study of Face Detection Algorithms for Masked Face Detection","created":"2023-05-18","cited_by_count":0,"area":null},{"id":"2309.17194","title":"Generalized Activation via Multivariate Projection","created":"2023-09-29","cited_by_count":0,"area":null},{"id":"2407.06087","title":"Analytic Convolutional Layer: A Step to Analytic Neural Network","created":"2024-07-03","cited_by_count":0,"area":null},{"id":"2411.18064","title":"Lightweight Gaze Estimation Model Via Fusion Global Information","created":"2024-11-27","cited_by_count":0,"area":null},{"id":"2508.05073","title":"ULU: A Unified Activation Function","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2603.05937","title":"Facial Expression Recognition Using Residual Masking Network","created":"2026-03-06","cited_by_count":0,"area":null}],"next_cursor":null}