{"total":146,"rows":[{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419,"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":"2310.17157","title":"Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time","created":"2023-10-26","cited_by_count":252,"area":null},{"id":"2303.01486","title":"Understanding plasticity in neural networks","created":"2023-03-02","cited_by_count":174,"area":null},{"id":"2206.00133","title":"Pre-training via Denoising for Molecular Property Prediction","created":"2022-05-31","cited_by_count":124,"area":null},{"id":"2112.01917","title":"A Structured Dictionary Perspective on Implicit Neural Representations","created":"2021-12-03","cited_by_count":100,"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":"2206.07085","title":"Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction","created":"2022-06-14","cited_by_count":86,"area":null},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2110.09456","title":"NormFormer: Improved Transformer Pretraining with Extra Normalization","created":"2021-10-18","cited_by_count":83,"area":null},{"id":"2503.10622","title":"Transformers without Normalization","created":"2025-03-13","cited_by_count":70,"area":null},{"id":"2309.16620","title":"Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit","created":"2023-09-28","cited_by_count":66,"area":null},{"id":"2202.11912","title":"A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributions","created":"2022-02-24","cited_by_count":64,"area":null},{"id":"2302.10322","title":"Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation","created":"2023-02-20","cited_by_count":45,"area":null},{"id":"2403.02241","title":"Neural Redshift: Random Networks are not Random Functions","created":"2024-03-04","cited_by_count":43,"area":null},{"id":"2410.01623","title":"Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?","created":"2024-10-02","cited_by_count":43,"area":null},{"id":"2311.01906","title":"Simplifying Transformer Blocks","created":"2023-11-03","cited_by_count":37,"area":null},{"id":"2106.04013","title":"The Future is Log-Gaussian: ResNets and Their Infinite-Depth-and-Width Limit at Initialization","created":"2021-06-07","cited_by_count":33,"area":null},{"id":"2111.11146","title":"On the Existence of Universal Lottery Tickets","created":"2021-11-22","cited_by_count":30,"area":null},{"id":"2110.12661","title":"ZerO Initialization: Initializing Neural Networks with only Zeros and Ones","created":"2021-10-25","cited_by_count":28,"area":null},{"id":"2202.03407","title":"Investigating the fidelity of explainable artificial intelligence methods for applications of convolutional neural networks in geoscience","created":"2022-02-07","cited_by_count":28,"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":"2303.00652","title":"Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science","created":"2023-03-01","cited_by_count":27,"area":null},{"id":"2206.04361","title":"Model Degradation Hinders Deep Graph Neural Networks","created":"2022-06-09","cited_by_count":26,"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":"2208.11342","title":"Discovering Transferable Forensic Features for CNN-generated Images Detection","created":"2022-08-24","cited_by_count":24,"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":"2106.03353","title":"Understanding Neural Code Intelligence Through Program Simplification","created":"2021-06-07","cited_by_count":22,"area":null},{"id":"2211.12486","title":"Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations","created":"2022-11-22","cited_by_count":22,"area":null},{"id":"2311.16681","title":"Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations","created":"2023-11-28","cited_by_count":22,"area":null},{"id":"2104.03093","title":"Spectral Analysis of the Neural Tangent Kernel for Deep Residual Networks","created":"2021-04-07","cited_by_count":21,"area":null},{"id":"2104.07916","title":"Augmenting Deep Classifiers with Polynomial Neural Networks","created":"2021-04-16","cited_by_count":21,"area":null},{"id":"2107.09370","title":"An Embedding of ReLU Networks and an Analysis of their Identifiability","created":"2021-07-20","cited_by_count":20,"area":null},{"id":"2106.15941","title":"Augmented Shortcuts for Vision Transformers","created":"2021-06-30","cited_by_count":19,"area":null},{"id":"2202.12270","title":"Evaluating Feature Attribution Methods in the Image Domain","created":"2022-02-22","cited_by_count":19,"area":null},{"id":"2104.08215","title":"\"BNN - BN = ?\": Training Binary Neural Networks without Batch Normalization","created":"2021-04-16","cited_by_count":17,"area":null},{"id":"2211.11426","title":"Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations","created":"2022-11-21","cited_by_count":17,"area":null},{"id":"2406.04280","title":"xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology","created":"2024-06-06","cited_by_count":16,"area":null},{"id":"2109.04236","title":"ECQ$^{\\text{x}}$: Explainability-Driven Quantization for Low-Bit and Sparse DNNs","created":"2021-09-09","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":"2302.07937","title":"The Expressive Power of Tuning Only the Normalization Layers","created":"2023-02-15","cited_by_count":13,"area":null},{"id":"2512.10938","title":"Stronger Normalization-Free Transformers","created":"2025-12-11","cited_by_count":13,"area":null},{"id":"2211.14810","title":"A Kernel Perspective of Skip Connections in Convolutional Networks","created":"2022-11-27","cited_by_count":12,"area":null},{"id":"2408.12568","title":"Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers","created":"2024-08-22","cited_by_count":11,"area":null},{"id":"2502.15886","title":"A Close Look at Decomposition-based XAI-Methods for Transformer Language Models","created":"2025-02-21","cited_by_count":11,"area":null},{"id":"2210.04153","title":"Stimulative Training of Residual Networks: A Social Psychology Perspective of Loafing","created":"2022-10-09","cited_by_count":10,"area":null},{"id":"2310.07235","title":"Are GATs Out of Balance?","created":"2023-10-11","cited_by_count":10,"area":null},{"id":"2403.08330","title":"Activating Wider Areas in Image Super-Resolution","created":"2024-03-13","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":"2102.07215","title":"Large-Scale Meta-Learning with Continual Trajectory Shifting","created":"2021-02-14","cited_by_count":9,"area":null},{"id":"2104.03114","title":"Learning Residue-Aware Correlation Filters and Refining Scale Estimates with the GrabCut for Real-Time UAV Tracking","created":"2021-04-07","cited_by_count":9,"area":null},{"id":"2302.01771","title":"Using Explainability to Inform Statistical Downscaling Based on Deep Learning Beyond Standard Validation Approaches","created":"2023-02-03","cited_by_count":9,"area":null},{"id":"2403.05583","title":"A Cross-Modal Approach to Silent Speech with LLM-Enhanced Recognition","created":"2024-03-02","cited_by_count":9,"area":null},{"id":"2405.06604","title":"Explaining Text Similarity in Transformer Models","created":"2024-05-10","cited_by_count":9,"area":null},{"id":"2409.01696","title":"On the Vulnerability of Skip Connections to Model Inversion Attacks","created":"2024-09-03","cited_by_count":9,"area":null},{"id":"2109.12935","title":"Time Series Model Attribution Visualizations as Explanations","created":"2021-09-27","cited_by_count":8,"area":null},{"id":"2506.14698","title":"Towards Desiderata-Driven Design of Visual Counterfactual Explainers","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2212.10522","title":"Transformers Go for the LOLs: Generating (Humourous) Titles from Scientific Abstracts End-to-End","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2305.02507","title":"Stimulative Training++: Go Beyond The Performance Limits of Residual Networks","created":"2023-05-04","cited_by_count":6,"area":null},{"id":"2305.07715","title":"Field theory for optimal signal propagation in ResNets","created":"2023-05-12","cited_by_count":6,"area":null},{"id":"2409.07787","title":"Stable Language Model Pre-training by Reducing Embedding Variability","created":"2024-09-12","cited_by_count":6,"area":null},{"id":"2506.02138","title":"Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2111.00687","title":"RMNet: Equivalently Removing Residual Connection from Networks","created":"2021-11-01","cited_by_count":5,"area":null},{"id":"2204.00826","title":"Online Convolutional Re-parameterization","created":"2022-04-02","cited_by_count":5,"area":null},{"id":"2303.09171","title":"Empowering CAM-Based Methods with Capability to Generate Fine-Grained and High-Faithfulness Explanations","created":"2023-03-16","cited_by_count":5,"area":null},{"id":"2403.11199","title":"Graph Unitary Message Passing","created":"2024-03-17","cited_by_count":5,"area":null},{"id":"2503.23313","title":"SpINR: Neural Volumetric Reconstruction for FMCW Radars","created":"2025-03-30","cited_by_count":5,"area":null},{"id":"2602.09009","title":"ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling","created":"2026-02-09","cited_by_count":5,"area":null},{"id":"2110.11150","title":"Lottery Tickets with Nonzero Biases","created":"2021-10-21","cited_by_count":4,"area":null},{"id":"2203.07861","title":"Don't Get Me Wrong: How to Apply Deep Visual Interpretations to Time Series","created":"2022-03-14","cited_by_count":4,"area":null},{"id":"2204.09498","title":"Backdooring Explainable Machine Learning","created":"2022-04-20","cited_by_count":4,"area":null},{"id":"2205.05662","title":"Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis","created":"2022-05-11","cited_by_count":4,"area":null},{"id":"2206.01261","title":"Entangled Residual Mappings","created":"2022-06-02","cited_by_count":4,"area":null},{"id":"2211.17180","title":"Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think","created":"2022-11-30","cited_by_count":4,"area":null},{"id":"2212.00026","title":"Data-driven Science and Machine Learning Methods in Laser-Plasma Physics","created":"2022-11-30","cited_by_count":4,"area":null},{"id":"2212.07047","title":"Shared Coupling-bridge for Weakly Supervised Local Feature Learning","created":"2022-12-14","cited_by_count":4,"area":null},{"id":"2302.03064","title":"Investigating Pulse-Echo Sound Speed Estimation in Breast Ultrasound with Deep Learning","created":"2023-02-06","cited_by_count":4,"area":null},{"id":"2410.10609","title":"Lambda-Skip Connections: the architectural component that prevents Rank Collapse","created":"2024-10-14","cited_by_count":4,"area":null},{"id":"2501.17086","title":"Accelerated Training through Iterative Gradient Propagation Along the Residual Path","created":"2025-01-28","cited_by_count":4,"area":null},{"id":"2506.09714","title":"Auto-Compressing Networks","created":"2025-06-11","cited_by_count":4,"area":null},{"id":"2103.04331","title":"Auto-tuning of Deep Neural Networks by Conflicting Layer Removal","created":"2021-03-07","cited_by_count":3,"area":null},{"id":"2104.02548","title":"White Box Methods for Explanations of Convolutional Neural Networks in Image Classification Tasks","created":"2021-04-06","cited_by_count":3,"area":null},{"id":"2211.08425","title":"A Rigorous Study Of The Deep Taylor Decomposition","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2301.05816","title":"Understanding the Spectral Bias of Coordinate Based MLPs Via Training Dynamics","created":"2023-01-14","cited_by_count":3,"area":null},{"id":"2305.14395","title":"Towards credible visual model interpretation with path attribution","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2307.09591","title":"Saliency strikes back: How filtering out high frequencies improves white-box explanations","created":"2023-07-18","cited_by_count":3,"area":null},{"id":"2401.06122","title":"Manipulating Feature Visualizations with Gradient Slingshots","created":"2024-01-11","cited_by_count":3,"area":null},{"id":"2406.13724","title":"Heterogeneous Graph Neural Networks with Post-hoc Explanations for Multi-modal and Explainable Land Use Inference","created":"2024-06-19","cited_by_count":3,"area":null},{"id":"2406.17792","title":"Applications of interpretable deep learning in neuroimaging: a comprehensive review","created":"2024-05-30","cited_by_count":3,"area":null},{"id":"2603.17048","title":"SCE-LITE-HQ: Smooth visual counterfactual explanations with generative foundation models","created":"2026-03-17","cited_by_count":3,"area":null},{"id":"2101.01214","title":"Reconstructing Patchy Reionization with Deep Learning","created":"2021-01-04","cited_by_count":2,"area":null},{"id":"2109.09715","title":"Reconstructing Cosmic Polarization Rotation with ResUNet-CMB","created":"2021-09-20","cited_by_count":2,"area":null},{"id":"2206.02761","title":"Dual Decomposition of Convex Optimization Layers for Consistent Attention in Medical Images","created":"2022-06-06","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":"2308.09381","title":"On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-box","created":"2023-08-18","cited_by_count":2,"area":null},{"id":"2310.20363","title":"Hidden Conflicts in Neural Networks and Their Implications for Explainability","created":"2023-10-31","cited_by_count":2,"area":null},{"id":"2508.10490","title":"On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2508.10595","title":"On Spectral Properties of Gradient-based Explanation Methods","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2602.13169","title":"Operator Learning for Families of Finite-State Mean-Field Games","created":"2026-02-13","cited_by_count":2,"area":null},{"id":"2606.03935","title":"Quadratic integrate-and-fire neurons exhibit less fragmented loss landscapes and outperform leaky integrate-and-fire neurons in spike-based gradient descent","created":"2026-06-02","cited_by_count":2,"area":null}],"next_cursor":"100"}