{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"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":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"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":"2012.07463","title":"Parameter-Efficient Transfer Learning with Diff Pruning","created":"2020-12-14","cited_by_count":352},{"id":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"1602.01528","title":"EIE: Efficient Inference Engine on Compressed Deep Neural Network","created":"2016-02-04","cited_by_count":295},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294},{"id":"1701.05369","title":"Variational Dropout Sparsifies Deep Neural Networks","created":"2017-01-19","cited_by_count":265},{"id":"1909.08478","title":"Simple, Scalable Adaptation for Neural Machine Translation","created":"2019-09-18","cited_by_count":242},{"id":"1611.05198","title":"One-Shot Video Object Segmentation","created":"2016-11-16","cited_by_count":235},{"id":"1607.03250","title":"Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures","created":"2016-07-12","cited_by_count":221},{"id":"1705.07565","title":"Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon","created":"2017-05-22","cited_by_count":221},{"id":"2312.00785","title":"Sequential Modeling Enables Scalable Learning for Large Vision Models","created":"2023-12-01","cited_by_count":212},{"id":"2111.01998","title":"OpenPrompt: An Open-source Framework for Prompt-learning","created":"2021-11-03","cited_by_count":148},{"id":"2109.05687","title":"Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning","created":"2021-09-13","cited_by_count":146},{"id":"2110.07560","title":"Composable Sparse Fine-Tuning for Cross-Lingual Transfer","created":"2021-10-14","cited_by_count":144},{"id":"2211.15583","title":"On the Effectiveness of Parameter-Efficient Fine-Tuning","created":"2022-11-28","cited_by_count":141},{"id":"1711.05136","title":"Deep Rewiring: Training very sparse deep networks","created":"2017-11-14","cited_by_count":139},{"id":"2206.04673","title":"Neural Prompt Search","created":"2022-06-09","cited_by_count":135},{"id":"1611.05128","title":"Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning","created":"2016-11-16","cited_by_count":134},{"id":"1507.06149","title":"Data-free parameter pruning for Deep Neural Networks","created":"2015-07-22","cited_by_count":112},{"id":"2004.12406","title":"Masking as an Efficient Alternative to Finetuning for Pretrained Language Models","created":"2020-04-26","cited_by_count":93},{"id":"2107.00358","title":"Cross-domain Few-shot Learning with Task-specific Adapters","created":"2021-07-01","cited_by_count":80},{"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":"2212.03220","title":"Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning","created":"2022-12-06","cited_by_count":57},{"id":"2312.10136","title":"Gradient-based Parameter Selection for Efficient Fine-Tuning","created":"2023-12-15","cited_by_count":40},{"id":"2312.02923","title":"MoSA: Mixture of Sparse Adapters for Visual Efficient Tuning","created":"2023-12-05","cited_by_count":6},{"id":"2210.15114","title":"Faster Linear Algebra for Distance Matrices","created":"2022-10-27","cited_by_count":4}],"next_cursor":null}