{"list":"other","total":53,"rows":[{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"1903.08560","title":"Surprises in High-Dimensional Ridgeless Least Squares Interpolation","created":"2019-03-19","cited_by_count":513},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"2004.13912","title":"Neural Additive Models: Interpretable Machine Learning with Neural Nets","created":"2020-04-29","cited_by_count":319},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253},{"id":"1909.10893","title":"Recurrent Independent Mechanisms","created":"2019-09-24","cited_by_count":219},{"id":"1909.12673","title":"A Constructive Prediction of the Generalization Error Across Scales","created":"2019-09-27","cited_by_count":210},{"id":"2006.13198","title":"Spectral Bias and Task-Model Alignment Explain Generalization in Kernel Regression and Infinitely Wide Neural Networks","created":"2020-06-23","cited_by_count":166},{"id":"1901.10912","title":"A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms","created":"2019-01-30","cited_by_count":158},{"id":"2003.13661","title":"Multi-Task Reinforcement Learning with Soft Modularization","created":"2020-03-30","cited_by_count":143},{"id":"2209.06640","title":"Revisiting Neural Scaling Laws in Language and Vision","created":"2022-09-13","cited_by_count":132},{"id":"1711.01239","title":"Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning","created":"2017-11-03","cited_by_count":126},{"id":"1704.05526","title":"Learning to Reason: End-to-End Module Networks for Visual Question Answering","created":"2017-04-18","cited_by_count":125},{"id":"2109.10686","title":"Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers","created":"2021-09-22","cited_by_count":106},{"id":"1712.00961","title":"Learning Independent Causal Mechanisms","created":"2017-12-04","cited_by_count":105},{"id":"2010.11635","title":"Continual Learning in Low-rank Orthogonal Subspaces","created":"2020-10-22","cited_by_count":99},{"id":"2010.02066","title":"Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks","created":"2020-10-05","cited_by_count":98},{"id":"2105.15004","title":"Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime","created":"2021-05-31","cited_by_count":96},{"id":"2203.06176","title":"More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize","created":"2022-03-11","cited_by_count":91},{"id":"1601.01705","title":"Learning to Compose Neural Networks for Question Answering","created":"2016-01-07","cited_by_count":85},{"id":"2102.04074","title":"Learning Curve Theory","created":"2021-02-08","cited_by_count":85},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83},{"id":"1902.05546","title":"Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity","created":"2019-02-14","cited_by_count":70},{"id":"1810.09665","title":"A jamming transition from under- to over-parametrization affects loss landscape and generalization","created":"2018-10-22","cited_by_count":67},{"id":"1810.08591","title":"A Modern Take on the Bias-Variance Tradeoff in Neural Networks","created":"2018-10-19","cited_by_count":65},{"id":"2207.03337","title":"Factorizing Knowledge in Neural Networks","created":"2022-07-04","cited_by_count":59},{"id":"1806.10166","title":"Modular meta-learning","created":"2018-06-26","cited_by_count":51},{"id":"1904.12774","title":"Routing Networks and the Challenges of Modular and Compositional Computation","created":"2019-04-29","cited_by_count":50},{"id":"2006.16981","title":"Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules","created":"2020-06-30","cited_by_count":38},{"id":"2105.08710","title":"Fast and Slow Learning of Recurrent Independent Mechanisms","created":"2021-05-18","cited_by_count":36},{"id":"2206.02713","title":"Is a Modular Architecture Enough?","created":"2022-06-06","cited_by_count":36},{"id":"1807.04640","title":"Automatically Composing Representation Transformations as a Means for Generalization","created":"2018-07-12","cited_by_count":35},{"id":"1909.05557","title":"Modular Meta-Learning with Shrinkage","created":"2019-09-12","cited_by_count":31},{"id":"2010.13933","title":"Memorizing without overfitting: Bias, variance, and interpolation in over-parameterized models","created":"2020-10-26","cited_by_count":27},{"id":"2201.00042","title":"Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments","created":"2021-12-31","cited_by_count":25},{"id":"2207.01725","title":"How Much More Data Do I Need? Estimating Requirements for Downstream Tasks","created":"2022-07-04","cited_by_count":23},{"id":"1912.13503","title":"Side-Tuning: A Baseline for Network Adaptation via Additive Side Networks","created":"2019-12-31","cited_by_count":16},{"id":"1809.07878","title":"Learning Quickly to Plan Quickly Using Modular Meta-Learning","created":"2018-09-20","cited_by_count":15},{"id":"2106.08170","title":"How Modular Should Neural Module Networks Be for Systematic Generalization?","created":"2021-06-15","cited_by_count":15},{"id":"2110.12231","title":"Learning curves for Gaussian process regression with power-law priors and targets","created":"2021-10-23","cited_by_count":15},{"id":"2110.09419","title":"Compositional Attention: Disentangling Search and Retrieval","created":"2021-10-18","cited_by_count":12},{"id":"2006.07642","title":"Sample complexity and effective dimension for regression on manifolds","created":"2020-06-13","cited_by_count":8},{"id":"1806.02453","title":"Visual Reasoning by Progressive Module Networks","created":"2018-06-06","cited_by_count":7},{"id":"1812.07768","title":"Modular meta-learning in abstract graph networks for combinatorial generalization","created":"2018-12-19","cited_by_count":2},{"id":"2208.03753","title":"Learning Modular Structures That Generalize Out-of-Distribution","created":"2022-08-07","cited_by_count":1}],"next_cursor":null}