{"list":"other","total":64,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"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":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"1609.09106","title":"HyperNetworks","created":"2016-09-27","cited_by_count":1027},{"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":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"1604.03539","title":"Cross-stitch Networks for Multi-task Learning","created":"2016-04-12","cited_by_count":467},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459},{"id":"1702.08423","title":"Age Progression/Regression by Conditional Adversarial Autoencoder","created":"2017-02-27","cited_by_count":429},{"id":"2009.09796","title":"Multi-Task Learning with Deep Neural Networks: A Survey","created":"2020-09-10","cited_by_count":375},{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364},{"id":"2310.11454","title":"VeRA: Vector-based Random Matrix Adaptation","created":"2023-10-17","cited_by_count":300},{"id":"1606.02147","title":"ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation","created":"2016-06-07","cited_by_count":291},{"id":"2101.10382","title":"Curriculum Learning: A Survey","created":"2021-01-25","cited_by_count":259},{"id":"2210.07558","title":"DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation","created":"2022-10-14","cited_by_count":233},{"id":"1912.12854","title":"Pareto Multi-Task Learning","created":"2019-12-30","cited_by_count":224},{"id":"2305.12827","title":"Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models","created":"2023-05-22","cited_by_count":221},{"id":"2202.01017","title":"Multi-Task Learning as a Bargaining Game","created":"2022-02-02","cited_by_count":215},{"id":"1905.11604","title":"SGD on Neural Networks Learns Functions of Increasing Complexity","created":"2019-05-28","cited_by_count":204},{"id":"2010.06808","title":"Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout","created":"2020-10-14","cited_by_count":201},{"id":"2010.05874","title":"Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models","created":"2020-10-12","cited_by_count":169},{"id":"2108.06098","title":"FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning","created":"2021-08-13","cited_by_count":141},{"id":"2405.07813","title":"Localizing Task Information for Improved Model Merging and Compression","created":"2024-05-13","cited_by_count":131},{"id":"2010.04104","title":"Learning the Pareto Front with Hypernetworks","created":"2020-10-08","cited_by_count":125},{"id":"2404.19245","title":"HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning","created":"2024-04-30","cited_by_count":123},{"id":"2302.00294","title":"The geometry of hidden representations of large transformer models","created":"2023-02-01","cited_by_count":112},{"id":"2309.14859","title":"Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation","created":"2023-09-26","cited_by_count":109},{"id":"2111.10603","title":"Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning","created":"2021-11-20","cited_by_count":101},{"id":"2103.02631","title":"RotoGrad: Gradient Homogenization in Multitask Learning","created":"2021-03-03","cited_by_count":83},{"id":"2402.02030","title":"Panacea: Pareto Alignment via Preference Adaptation for LLMs","created":"2024-02-03","cited_by_count":80},{"id":"2306.03792","title":"FAMO: Fast Adaptive Multitask Optimization","created":"2023-06-06","cited_by_count":78},{"id":"2202.03091","title":"Auto-Lambda: Disentangling Dynamic Task Relationships","created":"2022-02-07","cited_by_count":73},{"id":"2402.09997","title":"LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild","created":"2024-02-15","cited_by_count":68},{"id":"2006.16434","title":"Efficient Continuous Pareto Exploration in Multi-Task Learning","created":"2020-06-29","cited_by_count":57},{"id":"2010.06313","title":"Controllable Pareto Multi-Task Learning","created":"2020-10-13","cited_by_count":51},{"id":"2211.11567","title":"Neural networks trained with SGD learn distributions of increasing complexity","created":"2022-11-21","cited_by_count":50},{"id":"2406.11909","title":"Mixture-of-Subspaces in Low-Rank Adaptation","created":"2024-06-16","cited_by_count":47},{"id":"2103.13392","title":"Scalable Pareto Front Approximation for Deep Multi-Objective Learning","created":"2021-03-24","cited_by_count":45},{"id":"2403.03432","title":"Mixture-of-LoRAs: An Efficient Multitask Tuning for Large Language Models","created":"2024-03-06","cited_by_count":38},{"id":"2210.09759","title":"Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models","created":"2022-10-18","cited_by_count":29},{"id":"2402.16828","title":"Training Neural Networks from Scratch with Parallel Low-Rank Adapters","created":"2024-02-26","cited_by_count":17},{"id":"2212.01130","title":"Improving Pareto Front Learning via Multi-Sample Hypernetworks","created":"2022-12-02","cited_by_count":16},{"id":"2407.04493","title":"PROUD: PaRetO-gUided Diffusion Model for Multi-objective Generation","created":"2024-07-05","cited_by_count":16},{"id":"1805.04949","title":"DeLS-3D: Deep Localization and Segmentation with a 3D Semantic Map","created":"2018-05-13","cited_by_count":5}],"next_cursor":null}