{"list":"other","total":73,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"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":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"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":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944},{"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":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"2204.04799","title":"DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning","created":"2022-04-10","cited_by_count":642},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"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":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459},{"id":"1910.04867","title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","created":"2019-10-01","cited_by_count":425},{"id":"1806.03962","title":"Rotation Equivariant CNNs for Digital Pathology","created":"2018-06-08","cited_by_count":422},{"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":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294},{"id":"2310.02575","title":"AdaMerging: Adaptive Model Merging for Multi-Task Learning","created":"2023-10-04","cited_by_count":252},{"id":"2202.01017","title":"Multi-Task Learning as a Bargaining Game","created":"2022-02-02","cited_by_count":215},{"id":"2306.07280","title":"Controlling Text-to-Image Diffusion by Orthogonal Finetuning","created":"2023-06-12","cited_by_count":208},{"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":"2001.06902","title":"MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning","created":"2020-01-19","cited_by_count":157},{"id":"2110.01786","title":"MoEfication: Transformer Feed-forward Layers are Mixtures of Experts","created":"2021-10-05","cited_by_count":152},{"id":"1906.03525","title":"Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation","created":"2019-06-08","cited_by_count":142},{"id":"2206.04673","title":"Neural Prompt Search","created":"2022-06-09","cited_by_count":135},{"id":"2212.03145","title":"FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer","created":"2022-12-06","cited_by_count":133},{"id":"1801.08297","title":"NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reduction","created":"2018-01-25","cited_by_count":127},{"id":"2006.01895","title":"Learning to Branch for Multi-Task Learning","created":"2020-06-02","cited_by_count":115},{"id":"2311.06243","title":"Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization","created":"2023-11-10","cited_by_count":114},{"id":"2110.04260","title":"Taming Sparsely Activated Transformer with Stochastic Experts","created":"2021-10-08","cited_by_count":113},{"id":"2310.18339","title":"When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications","created":"2023-10-21","cited_by_count":111},{"id":"2312.12379","title":"Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning","created":"2023-12-19","cited_by_count":106},{"id":"2006.04096","title":"Robust Learning Through Cross-Task Consistency","created":"2020-06-07","cited_by_count":105},{"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":"1901.08933","title":"Self-Supervised Generalisation with Meta Auxiliary Learning","created":"2019-01-25","cited_by_count":88},{"id":"2306.07967","title":"One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning","created":"2023-06-13","cited_by_count":85},{"id":"1709.02480","title":"Fine-Grained Car Detection for Visual Census Estimation","created":"2017-09-07","cited_by_count":76},{"id":"2303.08566","title":"Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning","created":"2023-03-15","cited_by_count":74},{"id":"2104.13874","title":"Exploring Relational Context for Multi-Task Dense Prediction","created":"2021-04-28","cited_by_count":71},{"id":"2305.19000","title":"Independent Component Alignment for Multi-Task Learning","created":"2023-05-30","cited_by_count":70},{"id":"2403.17749","title":"Multi-Task Dense Prediction via Mixture of Low-Rank Experts","created":"2024-03-26","cited_by_count":58},{"id":"1410.0342","title":"Generalized Low Rank Models","created":"2014-10-01","cited_by_count":55},{"id":"2210.03265","title":"Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks","created":"2022-10-07","cited_by_count":52},{"id":"2008.10292","title":"Automated Search for Resource-Efficient Branched Multi-Task Networks","created":"2020-08-24","cited_by_count":51},{"id":"1606.04038","title":"Trace Norm Regularised Deep Multi-Task Learning","created":"2016-06-13","cited_by_count":50},{"id":"1807.06708","title":"A Modulation Module for Multi-task Learning with Applications in Image Retrieval","created":"2018-07-17","cited_by_count":49},{"id":"1904.08492","title":"MultiNet++: Multi-Stream Feature Aggregation and Geometric Loss Strategy for Multi-Task Learning","created":"2019-04-15","cited_by_count":45},{"id":"2007.02693","title":"Auxiliary Learning by Implicit Differentiation","created":"2020-06-22","cited_by_count":45},{"id":"2307.15324","title":"TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts","created":"2023-07-28","cited_by_count":45},{"id":"2111.14893","title":"Learning Multiple Dense Prediction Tasks from Partially Annotated Data","created":"2021-11-29","cited_by_count":42},{"id":"2310.06234","title":"Efficient Adaptation of Large Vision Transformer via Adapter Re-Composing","created":"2023-10-10","cited_by_count":35},{"id":"2311.02684","title":"Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE","created":"2023-11-05","cited_by_count":25},{"id":"2204.07964","title":"Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection","created":"2022-04-17","cited_by_count":14},{"id":"1902.06565","title":"The Kalai-Smorodinski solution for many-objective Bayesian optimization","created":"2019-02-18","cited_by_count":13},{"id":"2307.07934","title":"Contrastive Multi-Task Dense Prediction","created":"2023-07-16","cited_by_count":8},{"id":"1904.05590","title":"Low-rank matrix recovery with Ky Fan 2-k-norm","created":"2019-04-11","cited_by_count":3}],"next_cursor":null}