{"total":260,"rows":[{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167,"area":null},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764,"area":null},{"id":"2105.08050","title":"Pay Attention to MLPs","created":"2021-05-17","cited_by_count":368,"area":null},{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360,"area":null},{"id":"2505.06708","title":"Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free","created":"2025-05-10","cited_by_count":283,"area":"moe"},{"id":"2102.08005","title":"TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation","created":"2021-02-16","cited_by_count":258,"area":null},{"id":"2205.12005","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","created":"2022-05-24","cited_by_count":187,"area":null},{"id":"2105.00304","title":"SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects","created":"2021-05-01","cited_by_count":104,"area":null},{"id":"2106.06295","title":"Going Beyond Linear Transformers with Recurrent Fast Weight Programmers","created":"2021-06-11","cited_by_count":89,"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":"2303.16900","title":"InceptionNeXt: When Inception Meets ConvNeXt","created":"2023-03-29","cited_by_count":86,"area":null},{"id":"2105.10446","title":"ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction","created":"2021-05-21","cited_by_count":84,"area":null},{"id":"2603.15031","title":"Attention Residuals","created":"2026-03-16","cited_by_count":65,"area":null},{"id":"2102.06289","title":"When and How Mixup Improves Calibration","created":"2021-02-11","cited_by_count":60,"area":null},{"id":"2404.02747","title":"Faster Diffusion via Temporal Attention Decomposition","created":"2024-04-03","cited_by_count":54,"area":"diffusion"},{"id":"2402.02622","title":"DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging","created":"2024-02-04","cited_by_count":53,"area":null},{"id":"2107.03436","title":"Tensor Methods in Computer Vision and Deep Learning","created":"2021-07-07","cited_by_count":52,"area":null},{"id":"2209.06520","title":"Scalable Spatiotemporal Graph Neural Networks","created":"2022-09-14","cited_by_count":52,"area":null},{"id":"2207.04630","title":"On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligence","created":"2022-07-11","cited_by_count":50,"area":"lr"},{"id":"2101.00590","title":"RegNet: Self-Regulated Network for Image Classification","created":"2021-01-03","cited_by_count":44,"area":null},{"id":"2209.15200","title":"An efficient encoder-decoder architecture with top-down attention for speech separation","created":"2022-09-30","cited_by_count":38,"area":null},{"id":"2103.15452","title":"Boosting the Speed of Entity Alignment 10*: Dual Attention Matching Network with Normalized Hard Sample Mining","created":"2021-03-29","cited_by_count":37,"area":null},{"id":"2208.08352","title":"FCN-Transformer Feature Fusion for Polyp Segmentation","created":"2022-08-17","cited_by_count":37,"area":null},{"id":"2101.00345","title":"Modeling Fine-Grained Entity Types with Box Embeddings","created":"2021-01-02","cited_by_count":36,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2404.11568","title":"On the Scalability of GNNs for Molecular Graphs","created":"2024-04-17","cited_by_count":36,"area":null},{"id":"2608.30320","title":"On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability","created":"2026-08-31","cited_by_count":35,"area":"moe"},{"id":"2105.13448","title":"Open-world Machine Learning: Applications, Challenges, and Opportunities","created":"2021-05-27","cited_by_count":34,"area":null},{"id":"2202.05826","title":"End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking","created":"2022-02-11","cited_by_count":33,"area":"lr"},{"id":"2106.03180","title":"Vision Transformers with Hierarchical Attention","created":"2021-06-06","cited_by_count":31,"area":null},{"id":"2303.16756","title":"Large Language Models for Healthcare Data Augmentation: An Example on Patient-Trial Matching","created":"2023-03-24","cited_by_count":30,"area":null},{"id":"2103.00791","title":"RAGA: Relation-aware Graph Attention Networks for Global Entity Alignment","created":"2021-03-01","cited_by_count":29,"area":null},{"id":"2311.05967","title":"Plasma Surrogate Modelling using Fourier Neural Operators","created":"2023-11-10","cited_by_count":29,"area":null},{"id":"2203.08120","title":"Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers","created":"2022-03-15","cited_by_count":28,"area":null},{"id":"2106.15684","title":"Alzheimer's Dementia Recognition Using Acoustic, Lexical, Disfluency and Speech Pause Features Robust to Noisy Inputs","created":"2021-06-29","cited_by_count":27,"area":null},{"id":"2110.08191","title":"Why don't people use character-level machine translation?","created":"2021-10-15","cited_by_count":27,"area":null},{"id":"2203.09176","title":"ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation","created":"2022-03-17","cited_by_count":27,"area":null},{"id":"2309.03160","title":"ResFields: Residual Neural Fields for Spatiotemporal Signals","created":"2023-09-06","cited_by_count":27,"area":null},{"id":"2103.01075","title":"OmniNet: Omnidirectional Representations from Transformers","created":"2021-03-01","cited_by_count":23,"area":null},{"id":"2102.01670","title":"Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network Optimization","created":"2021-02-02","cited_by_count":22,"area":null},{"id":"2105.07205","title":"Rethinking Skip Connection with Layer Normalization in Transformers and ResNets","created":"2021-05-15","cited_by_count":22,"area":null},{"id":"2110.10064","title":"Idiomatic Expression Identification using Semantic Compatibility","created":"2021-10-19","cited_by_count":19,"area":null},{"id":"2202.13473","title":"The Spectral Bias of Polynomial Neural Networks","created":"2022-02-27","cited_by_count":19,"area":null},{"id":"2311.15436","title":"Learning to Skip for Language Modeling","created":"2023-11-26","cited_by_count":19,"area":null},{"id":"2402.18039","title":"ResLoRA: Identity Residual Mapping in Low-Rank Adaption","created":"2024-02-28","cited_by_count":18,"area":null},{"id":"2211.03796","title":"Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy","created":"2022-11-07","cited_by_count":17,"area":null},{"id":"2601.05732","title":"mHC-lite: You Don't Need 20 Sinkhorn-Knopp Iterations","created":"2026-01-09","cited_by_count":17,"area":null},{"id":"2106.09668","title":"Multi-modal fusion with gating using audio, lexical and disfluency features for Alzheimer's Dementia recognition from spontaneous speech","created":"2021-06-17","cited_by_count":16,"area":null},{"id":"2106.12772","title":"Task-agnostic Continual Learning with Hybrid Probabilistic Models","created":"2021-06-24","cited_by_count":16,"area":null},{"id":"2206.01649","title":"Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules","created":"2022-06-03","cited_by_count":16,"area":null},{"id":"2203.11200","title":"Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily","created":"2022-03-19","cited_by_count":15,"area":null},{"id":"2405.14992","title":"Linking In-context Learning in Transformers to Human Episodic Memory","created":"2024-05-23","cited_by_count":15,"area":null},{"id":"2103.08147","title":"LARNet: Lie Algebra Residual Network for Face Recognition","created":"2021-03-15","cited_by_count":14,"area":null},{"id":"2111.09451","title":"Benchmarking and scaling of deep learning models for land cover image classification","created":"2021-11-18","cited_by_count":14,"area":null},{"id":"2110.14769","title":"Detecting Dementia from Speech and Transcripts using Transformers","created":"2021-10-27","cited_by_count":13,"area":null},{"id":"2205.00782","title":"Type-aware Embeddings for Multi-Hop Reasoning over Knowledge Graphs","created":"2022-05-02","cited_by_count":13,"area":"lr"},{"id":"2211.06088","title":"RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization","created":"2022-11-11","cited_by_count":13,"area":null},{"id":"2304.05352","title":"SPOT: Sequential Predictive Modeling of Clinical Trial Outcome with Meta-Learning","created":"2023-04-07","cited_by_count":13,"area":null},{"id":"2211.04591","title":"Learning to Follow Instructions in Text-Based Games","created":"2022-11-08","cited_by_count":12,"area":null},{"id":"2309.13482","title":"A Unified Scheme of ResNet and Softmax","created":"2023-09-23","cited_by_count":12,"area":null},{"id":"2110.13658","title":"Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?","created":"2021-10-26","cited_by_count":11,"area":null},{"id":"2202.02981","title":"Neural Tangent Kernel Analysis of Deep Narrow Neural Networks","created":"2022-02-07","cited_by_count":11,"area":null},{"id":"2407.06677","title":"Mixture-of-Modules: Reinventing Transformers as Dynamic Assemblies of Modules","created":"2024-07-09","cited_by_count":11,"area":null},{"id":"2203.12813","title":"Disentangleing Content and Fine-grained Prosody Information via Hybrid ASR Bottleneck Features for Voice Conversion","created":"2022-03-24","cited_by_count":10,"area":null},{"id":"2307.07928","title":"Reinforced Disentanglement for Face Swapping without Skip Connection","created":"2023-07-16","cited_by_count":10,"area":null},{"id":"2309.11197","title":"The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute","created":"2023-09-20","cited_by_count":10,"area":null},{"id":"2405.01725","title":"Development of Skip Connection in Deep Neural Networks for Computer Vision and Medical Image Analysis: A Survey","created":"2024-05-02","cited_by_count":10,"area":null},{"id":"2602.08064","title":"SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm","created":"2026-02-08","cited_by_count":10,"area":null},{"id":"2102.04801","title":"Automatic variational inference with cascading flows","created":"2021-02-09","cited_by_count":9,"area":null},{"id":"2103.09108","title":"Is it enough to optimize CNN architectures on ImageNet?","created":"2021-03-16","cited_by_count":9,"area":null},{"id":"2110.06427","title":"Dense Uncertainty Estimation","created":"2021-10-13","cited_by_count":9,"area":null},{"id":"2206.01741","title":"Patcher: Patch Transformers with Mixture of Experts for Precise Medical Image Segmentation","created":"2022-06-03","cited_by_count":9,"area":"moe"},{"id":"2207.08548","title":"GANDALF: Gated Adaptive Network for Deep Automated Learning of Features","created":"2022-07-18","cited_by_count":9,"area":null},{"id":"2303.09266","title":"SmartBERT: A Promotion of Dynamic Early Exiting Mechanism for Accelerating BERT Inference","created":"2023-03-16","cited_by_count":9,"area":"inference"},{"id":"2406.13215","title":"Neural Residual Diffusion Models for Deep Scalable Vision Generation","created":"2024-06-19","cited_by_count":9,"area":"diffusion"},{"id":"2601.00417","title":"Deep Delta Learning","created":"2026-01-01","cited_by_count":9,"area":null},{"id":"2603.20176","title":"LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis","created":"2026-03-20","cited_by_count":9,"area":null},{"id":"2111.03135","title":"Scaffolding Sets","created":"2021-11-04","cited_by_count":8,"area":null},{"id":"2112.05909","title":"Neural Attention Models in Deep Learning: Survey and Taxonomy","created":"2021-12-11","cited_by_count":8,"area":null},{"id":"2210.00185","title":"Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple Tasks","created":"2022-10-01","cited_by_count":8,"area":null},{"id":"2306.06205","title":"Morphosyntactic probing of multilingual BERT models","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2402.05424","title":"Neural Circuit Diagrams: Robust Diagrams for the Communication, Implementation, and Analysis of Deep Learning Architectures","created":"2024-02-08","cited_by_count":8,"area":null},{"id":"2508.08435","title":"Fast weight programming and linear transformers: from machine learning to neurobiology","created":"2025-08-11","cited_by_count":8,"area":null},{"id":"2510.07739","title":"MeSH: Memory-as-State-Highways for Recursive Transformers","created":"2025-10-09","cited_by_count":8,"area":null},{"id":"2104.03693","title":"Learning specialized activation functions with the Piecewise Linear Unit","created":"2021-04-08","cited_by_count":7,"area":null},{"id":"2106.12307","title":"Should You Go Deeper? Optimizing Convolutional Neural Network Architectures without Training by Receptive Field Analysis","created":"2021-06-23","cited_by_count":7,"area":null},{"id":"2208.01134","title":"Improving the Trainability of Deep Neural Networks through Layerwise Batch-Entropy Regularization","created":"2022-08-01","cited_by_count":7,"area":null},{"id":"2305.10544","title":"Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks","created":"2023-05-17","cited_by_count":7,"area":null},{"id":"2401.15741","title":"SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networks","created":"2024-01-28","cited_by_count":7,"area":null},{"id":"2502.02790","title":"Leveraging the true depth of LLMs","created":"2025-02-05","cited_by_count":7,"area":null},{"id":"2601.19895","title":"Post-LayerNorm Is Back: Stable, ExpressivE, and Deep","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2102.09808","title":"Improving Anytime Prediction with Parallel Cascaded Networks and a Temporal-Difference Loss","created":"2021-02-19","cited_by_count":6,"area":null},{"id":"2104.11008","title":"Unsupervised anomaly detection for a Smart Autonomous Robotic Assistant Surgeon (SARAS)using a deep residual autoencoder","created":"2021-04-22","cited_by_count":6,"area":null},{"id":"2111.05496","title":"ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees","created":"2021-11-10","cited_by_count":6,"area":null},{"id":"2307.08863","title":"Meta-Value Learning: a General Framework for Learning with Learning Awareness","created":"2023-07-17","cited_by_count":6,"area":null},{"id":"2103.08877","title":"Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling","created":"2021-03-16","cited_by_count":5,"area":null},{"id":"2106.08318","title":"Gradient Forward-Propagation for Large-Scale Temporal Video Modelling","created":"2021-06-15","cited_by_count":5,"area":null},{"id":"2107.07110","title":"Compact and Optimal Deep Learning with Recurrent Parameter Generators","created":"2021-07-15","cited_by_count":5,"area":null},{"id":"2203.12944","title":"Transformers Meet Visual Learning Understanding: A Comprehensive Review","created":"2022-03-24","cited_by_count":5,"area":null},{"id":"2209.01847","title":"Conflict-Aware Pseudo Labeling via Optimal Transport for Entity Alignment","created":"2022-09-05","cited_by_count":5,"area":null}],"next_cursor":"100"}