{"list":"other","total":57,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"1309.5549","title":"Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming","created":"2013-09-22","cited_by_count":724},{"id":"1604.03540","title":"Training Region-based Object Detectors with Online Hard Example Mining","created":"2016-04-12","cited_by_count":579},{"id":"1608.04636","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\\L{}ojasiewicz Condition","created":"2016-08-16","cited_by_count":539},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"1905.07553","title":"Which Tasks Should Be Learned Together in Multi-task Learning?","created":"2019-05-18","cited_by_count":375},{"id":"1704.04289","title":"Stochastic Gradient Descent as Approximate Bayesian Inference","created":"2017-04-13","cited_by_count":300},{"id":"1411.4357","title":"Sketching as a Tool for Numerical Linear Algebra","created":"2014-11-17","cited_by_count":288},{"id":"1812.06162","title":"An Empirical Model of Large-Batch Training","created":"2018-12-14","cited_by_count":281},{"id":"1705.08741","title":"Train longer, generalize better: closing the generalization gap in large batch training of neural networks","created":"2017-05-24","cited_by_count":279},{"id":"1702.01992","title":"Gated Multimodal Units for Information Fusion","created":"2017-02-07","cited_by_count":248},{"id":"1806.08730","title":"The Natural Language Decathlon: Multitask Learning as Question Answering","created":"2018-06-20","cited_by_count":236},{"id":"1912.12854","title":"Pareto Multi-Task Learning","created":"2019-12-30","cited_by_count":224},{"id":"2109.04617","title":"Efficiently Identifying Task Groupings for Multi-Task Learning","created":"2021-09-10","cited_by_count":222},{"id":"2202.01017","title":"Multi-Task Learning as a Bargaining Game","created":"2022-02-02","cited_by_count":215},{"id":"2107.07502","title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning","created":"2021-07-15","cited_by_count":146},{"id":"1710.06451","title":"A Bayesian Perspective on Generalization and Stochastic Gradient Descent","created":"2017-10-17","cited_by_count":135},{"id":"1506.08272","title":"Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization","created":"2015-06-27","cited_by_count":116},{"id":"2006.04096","title":"Robust Learning Through Cross-Task Consistency","created":"2020-06-07","cited_by_count":105},{"id":"1808.07275","title":"CentralNet: a Multilayer Approach for Multimodal Fusion","created":"2018-08-22","cited_by_count":86},{"id":"2306.03792","title":"FAMO: Fast Adaptive Multitask Optimization","created":"2023-06-06","cited_by_count":78},{"id":"2201.04122","title":"In Defense of the Unitary Scalarization for Deep Multi-Task Learning","created":"2022-01-11","cited_by_count":67},{"id":"1801.02143","title":"Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction","created":"2018-01-07","cited_by_count":61},{"id":"1602.02666","title":"A Variational Analysis of Stochastic Gradient Algorithms","created":"2016-02-08","cited_by_count":57},{"id":"2302.11289","title":"Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learning","created":"2023-02-22","cited_by_count":51},{"id":"2102.02410","title":"A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network","created":"2021-02-04","cited_by_count":47},{"id":"1501.01711","title":"Frequent Directions : Simple and Deterministic Matrix Sketching","created":"2015-01-08","cited_by_count":39},{"id":"2402.15638","title":"Fair Resource Allocation in Multi-Task Learning","created":"2024-02-23","cited_by_count":35},{"id":"2211.15055","title":"AdaTask: A Task-aware Adaptive Learning Rate Approach to Multi-task Learning","created":"2022-11-28","cited_by_count":31},{"id":"1605.09774","title":"Asynchrony begets Momentum, with an Application to Deep Learning","created":"2016-05-31","cited_by_count":30},{"id":"2408.02686","title":"A Systematic Review of Intermediate Fusion in Multimodal Deep Learning for Biomedical Applications","created":"2024-08-02","cited_by_count":25},{"id":"2402.02009","title":"Robust Multi-Task Learning with Excess Risks","created":"2024-02-03","cited_by_count":24},{"id":"2502.11986","title":"Selective Task Group Updates for Multi-Task Optimization","created":"2025-02-17","cited_by_count":17},{"id":"2411.18615","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","created":"2024-11-27","cited_by_count":12},{"id":"2404.06486","title":"GO4Align: Group Optimization for Multi-Task Alignment","created":"2024-04-09","cited_by_count":11},{"id":"2310.07361","title":"Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters","created":"2023-10-11","cited_by_count":9},{"id":"2002.04792","title":"A Simple General Approach to Balance Task Difficulty in Multi-Task Learning","created":"2020-02-12","cited_by_count":8},{"id":"2506.06130","title":"Gradient Similarity Surgery in Multi-Task Deep Learning","created":"2025-06-06","cited_by_count":5},{"id":"2012.07966","title":"Odd-One-Out Representation Learning","created":"2020-12-14","cited_by_count":4},{"id":"2310.16241","title":"Task Grouping for Automated Multi-Task Machine Learning via Task Affinity Prediction","created":"2023-10-24","cited_by_count":4},{"id":"2103.09488","title":"Revisiting the Loss Weight Adjustment in Object Detection","created":"2021-03-17","cited_by_count":3},{"id":"2302.09352","title":"MaxGNR: A Dynamic Weight Strategy via Maximizing Gradient-to-Noise Ratio for Multi-Task Learning","created":"2023-02-18","cited_by_count":3},{"id":"2307.03374","title":"STG-MTL: Scalable Task Grouping for Multi-Task Learning Using Data Map","created":"2023-07-07","cited_by_count":3},{"id":"2402.15328","title":"Towards Principled Task Grouping for Multi-Task Learning","created":"2024-02-23","cited_by_count":3}],"next_cursor":null}