{"total":493,"rows":[{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968,"area":null},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627,"area":null},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579,"area":null},{"id":"2106.10689","title":"NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction","created":"2021-06-20","cited_by_count":1712,"area":null},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616,"area":null},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167,"area":null},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758,"area":null},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687,"area":null},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680,"area":null},{"id":"2102.07623","title":"FedBN: Federated Learning on Non-IID Features via Local Batch Normalization","created":"2021-02-15","cited_by_count":571,"area":null},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568,"area":null},{"id":"2111.12797","title":"ReAct: Out-of-distribution Detection With Rectified Activations","created":"2021-11-24","cited_by_count":486,"area":null},{"id":"2101.10994","title":"Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes","created":"2021-01-26","cited_by_count":426,"area":null},{"id":"2204.10377","title":"Contrastive Test-Time Adaptation","created":"2022-04-21","cited_by_count":261,"area":null},{"id":"2103.10428","title":"Large Scale Image Completion via Co-Modulated Generative Adversarial Networks","created":"2021-03-18","cited_by_count":220,"area":null},{"id":"2106.14448","title":"R-Drop: Regularized Dropout for Neural Networks","created":"2021-06-28","cited_by_count":202,"area":null},{"id":"2110.04202","title":"Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation","created":"2021-10-08","cited_by_count":177,"area":null},{"id":"2303.06296","title":"Stabilizing Transformer Training by Preventing Attention Entropy Collapse","created":"2023-03-11","cited_by_count":161,"area":null},{"id":"2106.02073","title":"Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path","created":"2021-06-03","cited_by_count":158,"area":null},{"id":"2103.06871","title":"SMPLicit: Topology-aware Generative Model for Clothed People","created":"2021-03-11","cited_by_count":155,"area":null},{"id":"2303.00654","title":"How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy","created":"2023-03-01","cited_by_count":153,"area":null},{"id":"2210.10036","title":"ARAH: Animatable Volume Rendering of Articulated Human SDFs","created":"2022-10-18","cited_by_count":139,"area":null},{"id":"2312.03704","title":"Relightable Gaussian Codec Avatars","created":"2023-12-06","cited_by_count":127,"area":null},{"id":"2308.08468","title":"An Expert's Guide to Training Physics-informed Neural Networks","created":"2023-08-16","cited_by_count":126,"area":null},{"id":"2102.02611","title":"CKConv: Continuous Kernel Convolution For Sequential Data","created":"2021-02-04","cited_by_count":120,"area":null},{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118,"area":null},{"id":"2203.14197","title":"Long-Tailed Recognition via Weight Balancing","created":"2022-03-27","cited_by_count":107,"area":null},{"id":"2104.07167","title":"Orthogonalizing Convolutional Layers with the Cayley Transform","created":"2021-04-14","cited_by_count":105,"area":null},{"id":"2106.14103","title":"PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs","created":"2021-06-26","cited_by_count":98,"area":null},{"id":"2206.04041","title":"Neural Collapse: A Review on Modelling Principles and Generalization","created":"2022-06-08","cited_by_count":95,"area":null},{"id":"2205.04183","title":"Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation","created":"2022-05-09","cited_by_count":94,"area":null},{"id":"2209.15076","title":"3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation","created":"2022-09-29","cited_by_count":94,"area":null},{"id":"2104.00702","title":"NPMs: Neural Parametric Models for 3D Deformable Shapes","created":"2021-04-01","cited_by_count":90,"area":null},{"id":"2101.08692","title":"Characterizing signal propagation to close the performance gap in unnormalized ResNets","created":"2021-01-21","cited_by_count":88,"area":null},{"id":"2105.10422","title":"LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond","created":"2021-05-21","cited_by_count":88,"area":null},{"id":"2210.09298","title":"What Makes Convolutional Models Great on Long Sequence Modeling?","created":"2022-10-17","cited_by_count":87,"area":null},{"id":"2308.16692","title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models","created":"2023-08-31","cited_by_count":87,"area":null},{"id":"2110.01654","title":"Improved architectures and training algorithms for deep operator networks","created":"2021-10-04","cited_by_count":86,"area":null},{"id":"2202.08345","title":"Learning Smooth Neural Functions via Lipschitz Regularization","created":"2022-02-16","cited_by_count":86,"area":null},{"id":"2206.07085","title":"Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction","created":"2022-06-14","cited_by_count":86,"area":null},{"id":"2105.02201","title":"PD-GAN: Probabilistic Diverse GAN for Image Inpainting","created":"2021-05-05","cited_by_count":80,"area":null},{"id":"2310.11230","title":"Zipformer: A faster and better encoder for automatic speech recognition","created":"2023-10-17","cited_by_count":80,"area":null},{"id":"2111.14826","title":"Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation","created":"2021-11-29","cited_by_count":79,"area":null},{"id":"2104.01845","title":"Unsupervised Multi-source Domain Adaptation Without Access to Source Data","created":"2021-04-05","cited_by_count":76,"area":null},{"id":"2106.14342","title":"Stabilizing Equilibrium Models by Jacobian Regularization","created":"2021-06-28","cited_by_count":72,"area":null},{"id":"2307.00379","title":"Residual-based attention in physics-informed neural networks","created":"2023-07-01","cited_by_count":72,"area":null},{"id":"2108.08487","title":"Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain","created":"2021-08-19","cited_by_count":71,"area":null},{"id":"2410.01131","title":"nGPT: Normalized Transformer with Representation Learning on the Hypersphere","created":"2024-10-01","cited_by_count":70,"area":null},{"id":"2503.10622","title":"Transformers without Normalization","created":"2025-03-13","cited_by_count":70,"area":null},{"id":"2105.05246","title":"Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective","created":"2021-05-11","cited_by_count":65,"area":null},{"id":"2303.03770","title":"Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptation","created":"2023-03-07","cited_by_count":65,"area":null},{"id":"2206.06640","title":"Confidence Score for Source-Free Unsupervised Domain Adaptation","created":"2022-06-14","cited_by_count":59,"area":null},{"id":"2102.08248","title":"Hierarchical VAEs Know What They Don't Know","created":"2021-02-16","cited_by_count":58,"area":null},{"id":"2206.08009","title":"Balancing Discriminability and Transferability for Source-Free Domain Adaptation","created":"2022-06-16","cited_by_count":58,"area":null},{"id":"2502.00604","title":"Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective","created":"2025-02-02","cited_by_count":56,"area":null},{"id":"2305.17212","title":"Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks","created":"2023-05-26","cited_by_count":53,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2104.01539","title":"DINE: Domain Adaptation from Single and Multiple Black-box Predictors","created":"2021-04-04","cited_by_count":51,"area":null},{"id":"2105.02716","title":"Noether's Learning Dynamics: Role of Symmetry Breaking in Neural Networks","created":"2021-05-06","cited_by_count":50,"area":null},{"id":"2303.17132","title":"C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation","created":"2023-03-30","cited_by_count":50,"area":null},{"id":"2203.11947","title":"CM-GAN: Image Inpainting with Cascaded Modulation GAN and Object-Aware Training","created":"2022-03-22","cited_by_count":49,"area":null},{"id":"2205.06924","title":"A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Model","created":"2022-05-13","cited_by_count":44,"area":null},{"id":"2103.07531","title":"Uncertainty-guided Model Generalization to Unseen Domains","created":"2021-03-12","cited_by_count":41,"area":null},{"id":"2207.14067","title":"Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images","created":"2022-07-28","cited_by_count":40,"area":null},{"id":"2201.08025","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","created":"2022-01-20","cited_by_count":39,"area":null},{"id":"2211.09961","title":"Path Independent Equilibrium Models Can Better Exploit Test-Time Computation","created":"2022-11-18","cited_by_count":38,"area":null},{"id":"2204.00604","title":"Quantized GAN for Complex Music Generation from Dance Videos","created":"2022-04-01","cited_by_count":37,"area":null},{"id":"2205.06254","title":"Learned Vertex Descent: A New Direction for 3D Human Model Fitting","created":"2022-05-12","cited_by_count":37,"area":null},{"id":"2506.13018","title":"Symmetry in Neural Network Parameter Spaces","created":"2025-06-16","cited_by_count":36,"area":null},{"id":"2106.06842","title":"Recomposing the Reinforcement Learning Building Blocks with Hypernetworks","created":"2021-06-12","cited_by_count":35,"area":null},{"id":"2205.15439","title":"StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesis","created":"2022-05-30","cited_by_count":33,"area":null},{"id":"2104.05097","title":"Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networks","created":"2021-04-11","cited_by_count":30,"area":null},{"id":"2212.00613","title":"NeuWigs: A Neural Dynamic Model for Volumetric Hair Capture and Animation","created":"2022-12-01","cited_by_count":30,"area":null},{"id":"2109.02220","title":"GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization","created":"2021-09-06","cited_by_count":29,"area":null},{"id":"2202.00980","title":"Robust Training of Neural Networks Using Scale Invariant Architectures","created":"2022-02-02","cited_by_count":29,"area":null},{"id":"2110.11222","title":"Is High Variance Unavoidable in RL? A Case Study in Continuous Control","created":"2021-10-21","cited_by_count":28,"area":null},{"id":"2203.04559","title":"Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition","created":"2022-03-09","cited_by_count":28,"area":null},{"id":"2206.04459","title":"SDQ: Stochastic Differentiable Quantization with Mixed Precision","created":"2022-06-09","cited_by_count":28,"area":null},{"id":"2406.06248","title":"Compute Better Spent: Replacing Dense Layers with Structured Matrices","created":"2024-06-10","cited_by_count":28,"area":null},{"id":"2110.02470","title":"SSFL: Tackling Label Deficiency in Federated Learning via Personalized Self-Supervision","created":"2021-10-06","cited_by_count":27,"area":null},{"id":"2104.02847","title":"Deep Implicit Statistical Shape Models for 3D Medical Image Delineation","created":"2021-04-07","cited_by_count":26,"area":null},{"id":"2102.03340","title":"NRTSI: Non-Recurrent Time Series Imputation","created":"2021-02-05","cited_by_count":25,"area":null},{"id":"2106.05956","title":"Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning","created":"2021-06-10","cited_by_count":25,"area":null},{"id":"2409.04720","title":"A Comprehensive Survey on Evidential Deep Learning and Its Applications","created":"2024-09-07","cited_by_count":25,"area":null},{"id":"2102.07227","title":"Learning by Turning: Neural Architecture Aware Optimisation","created":"2021-02-14","cited_by_count":23,"area":null},{"id":"2203.13903","title":"Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection","created":"2022-03-25","cited_by_count":23,"area":null},{"id":"2208.11602","title":"Motion Robust High-Speed Light-Weighted Object Detection With Event Camera","created":"2022-08-24","cited_by_count":23,"area":null},{"id":"2301.08128","title":"EPiC-GAN: Equivariant Point Cloud Generation for Particle Jets","created":"2023-01-17","cited_by_count":23,"area":null},{"id":"2107.04205","title":"On the Variance of the Fisher Information for Deep Learning","created":"2021-07-09","cited_by_count":22,"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":"2103.01499","title":"Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization","created":"2021-03-02","cited_by_count":21,"area":null},{"id":"2103.03158","title":"A Structural Causal Model for MR Images of Multiple Sclerosis","created":"2021-03-04","cited_by_count":21,"area":null},{"id":"2207.13247","title":"Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation","created":"2022-07-27","cited_by_count":21,"area":null},{"id":"2310.18605","title":"TorchDEQ: A Library for Deep Equilibrium Models","created":"2023-10-28","cited_by_count":21,"area":null},{"id":"2502.10385","title":"Simplifying DINO via Coding Rate Regularization","created":"2025-02-14","cited_by_count":21,"area":null},{"id":"2106.15739","title":"On the Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay","created":"2021-06-29","cited_by_count":20,"area":null},{"id":"2506.03133","title":"PoLAR: Polar-Decomposed Low-Rank Adapter Representation","created":"2025-06-03","cited_by_count":20,"area":null},{"id":"2106.01151","title":"Towards Deeper Deep Reinforcement Learning with Spectral Normalization","created":"2021-06-02","cited_by_count":19,"area":null},{"id":"2203.07976","title":"On the Pitfalls of Batch Normalization for End-to-End Video Learning: A Study on Surgical Workflow Analysis","created":"2022-03-15","cited_by_count":19,"area":null},{"id":"2402.07193","title":"Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent","created":"2024-02-11","cited_by_count":19,"area":null}],"next_cursor":"100"}