{"total":33,"rows":[{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189,"area":null},{"id":"2105.10585","title":"Properties of the After Kernel","created":"2021-05-21","cited_by_count":27,"area":null},{"id":"2405.16391","title":"When does compositional structure yield compositional generalization? A kernel theory","created":"2024-05-26","cited_by_count":20,"area":null},{"id":"2106.08704","title":"Memorization and Generalization in Neural Code Intelligence Models","created":"2021-06-16","cited_by_count":19,"area":null},{"id":"2412.07684","title":"The Pitfalls of Memorization: When Memorization Hurts Generalization","created":"2024-12-10","cited_by_count":19,"area":null},{"id":"2102.12238","title":"Inductive Bias of Multi-Channel Linear Convolutional Networks with Bounded Weight Norm","created":"2021-02-24","cited_by_count":18,"area":null},{"id":"2406.03880","title":"Memorization in deep learning: A survey","created":"2024-06-06","cited_by_count":15,"area":null},{"id":"2102.08373","title":"Analysis of feature learning in weight-tied autoencoders via the mean field lens","created":"2021-02-16","cited_by_count":14,"area":null},{"id":"2305.17895","title":"ReSup: Reliable Label Noise Suppression for Facial Expression Recognition","created":"2023-05-29","cited_by_count":14,"area":null},{"id":"2104.00613","title":"The surprising impact of mask-head architecture on novel class segmentation","created":"2021-04-01","cited_by_count":13,"area":null},{"id":"2106.07140","title":"SinIR: Efficient General Image Manipulation with Single Image Reconstruction","created":"2021-06-14","cited_by_count":13,"area":null},{"id":"2307.00310","title":"Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD","created":"2023-07-01","cited_by_count":11,"area":null},{"id":"2505.22785","title":"Navigating the Latent Space Dynamics of Neural Models","created":"2025-05-28","cited_by_count":8,"area":null},{"id":"2310.05337","title":"What do larger image classifiers memorise?","created":"2023-10-09","cited_by_count":6,"area":null},{"id":"2311.03873","title":"Mini but Mighty: Finetuning ViTs with Mini Adapters","created":"2023-11-07","cited_by_count":6,"area":null},{"id":"2506.01855","title":"Trade-offs in Data Memorization via Strong Data Processing Inequalities","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2106.15456","title":"A Mechanism for Producing Aligned Latent Spaces with Autoencoders","created":"2021-06-29","cited_by_count":5,"area":null},{"id":"2402.14482","title":"SpanSeq: Similarity-based sequence data splitting method for improved development and assessment of deep learning projects","created":"2024-02-22","cited_by_count":5,"area":null},{"id":"2202.12637","title":"Do autoencoders need a bottleneck for anomaly detection?","created":"2022-02-25","cited_by_count":3,"area":null},{"id":"2310.12977","title":"Training Dynamics of Deep Network Linear Regions","created":"2023-10-19","cited_by_count":3,"area":null},{"id":"2209.09844","title":"Frequency Dropout: Feature-Level Regularization via Randomized Filtering","created":"2022-09-20","cited_by_count":2,"area":null},{"id":"2310.04015","title":"Anonymous Learning via Look-Alike Clustering: A Precise Analysis of Model Generalization","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2108.13203","title":"Feature Importance in a Deep Learning Climate Emulator","created":"2021-08-27","cited_by_count":1,"area":null},{"id":"2301.04900","title":"Stretched and measured neural predictions of complex network dynamics","created":"2023-01-12","cited_by_count":1,"area":null},{"id":"2306.09991","title":"Evolutionary Algorithms in the Light of SGD: Limit Equivalence, Minima Flatness, and Transfer Learning","created":"2023-05-20","cited_by_count":1,"area":null},{"id":"2404.01536","title":"Laying Anchors: Semantically Priming Numerals in Language Modeling","created":"2024-04-02","cited_by_count":1,"area":null},{"id":"2409.13163","title":"Hidden Activations Are Not Enough: A General Approach to Neural Network Predictions","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2411.19640","title":"Learned Random Label Predictions as a Neural Network Complexity Metric","created":"2024-11-29","cited_by_count":1,"area":null},{"id":"2211.05624","title":"Improving the Robustness of Neural Multiplication Units with Reversible Stochasticity","created":"2022-11-10","cited_by_count":0,"area":null},{"id":"2312.00072","title":"CRAFT: Contextual Re-Activation of Filters for face recognition Training","created":"2023-11-29","cited_by_count":0,"area":null},{"id":"2404.05484","title":"What is Intelligence? A Cycle Closure Perspective","created":"2024-04-08","cited_by_count":0,"area":null},{"id":"2505.12960","title":"Hardware-Adaptive and Superlinear-Capacity Memristor-based Associative Memory","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2607.11541","title":"Random Label Prediction Heads for Studying Memorization in Deep Neural Networks","created":"2026-07-13","cited_by_count":0,"area":null}],"next_cursor":null}