{"total":18,"rows":[{"id":"2305.16380","title":"Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer","created":"2023-05-25","cited_by_count":102,"area":null},{"id":"2310.00535","title":"JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention","created":"2023-10-01","cited_by_count":52,"area":null},{"id":"2103.00841","title":"Learning Frequency Domain Approximation for Binary Neural Networks","created":"2021-03-01","cited_by_count":38,"area":null},{"id":"2406.02997","title":"Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs","created":"2024-06-05","cited_by_count":34,"area":null},{"id":"2302.10034","title":"Over-Parameterization Exponentially Slows Down Gradient Descent for Learning a Single Neuron","created":"2023-02-20","cited_by_count":25,"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":"2106.15941","title":"Augmented Shortcuts for Vision Transformers","created":"2021-06-30","cited_by_count":19,"area":null},{"id":"2104.08903","title":"SurvNAM: The machine learning survival model explanation","created":"2021-04-18","cited_by_count":16,"area":null},{"id":"2203.15664","title":"Nearly Minimax Algorithms for Linear Bandits with Shared Representation","created":"2022-03-29","cited_by_count":16,"area":null},{"id":"2405.00985","title":"Progressive Feedforward Collapse of ResNet Training","created":"2024-05-02","cited_by_count":12,"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":"2506.05249","title":"On the Convergence of Gradient Descent on Learning Transformers with Residual Connections","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2305.18506","title":"Generalization Ability of Wide Residual Networks","created":"2023-05-29","cited_by_count":5,"area":null},{"id":"2411.02139","title":"Theoretical characterisation of the Gauss-Newton conditioning in Neural Networks","created":"2024-11-04","cited_by_count":5,"area":null},{"id":"2501.00243","title":"Cross-Layer Cache Aggregation for Token Reduction in Ultra-Fine-Grained Image Recognition","created":"2024-12-31","cited_by_count":1,"area":null},{"id":"2506.24120","title":"Data Uniformity Improves Training Efficiency and More, with a Convergence Framework Beyond the NTK Regime","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2210.10725","title":"SML:Enhance the Network Smoothness with Skip Meta Logit for CTR Prediction","created":"2022-10-09","cited_by_count":0,"area":null},{"id":"2607.23994","title":"Effective Receptive Field Ordering Matters for Infrared Small Target Detection","created":"2026-07-27","cited_by_count":0,"area":null}],"next_cursor":null}