{"list":"other","total":61,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2010.08895","title":"Fourier Neural Operator for Parametric Partial Differential Equations","created":"2020-10-18","cited_by_count":2908},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1609.05158","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","created":"2016-09-16","cited_by_count":1204},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"2207.01848","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","created":"2022-07-05","cited_by_count":674},{"id":"1802.03601","title":"Deep Visual Domain Adaptation: A Survey","created":"2018-02-10","cited_by_count":635},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"1407.7722","title":"OpenML: networked science in machine learning","created":"2014-07-29","cited_by_count":526},{"id":"1801.10130","title":"Spherical CNNs","created":"2018-01-30","cited_by_count":456},{"id":"2210.07182","title":"PDEBENCH: An Extensive Benchmark for Scientific Machine Learning","created":"2022-10-13","cited_by_count":413},{"id":"2003.06505","title":"AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data","created":"2020-03-13","cited_by_count":383},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344},{"id":"2010.00475","title":"FSD50K: An Open Dataset of Human-Labeled Sound Events","created":"2020-10-01","cited_by_count":342},{"id":"1910.13051","title":"ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels","created":"2019-10-29","cited_by_count":339},{"id":"2203.17274","title":"Exploring Visual Prompts for Adapting Large-Scale Models","created":"2022-03-31","cited_by_count":274},{"id":"1901.02985","title":"Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation","created":"2019-01-10","cited_by_count":260},{"id":"1911.03437","title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","created":"2019-11-08","cited_by_count":254},{"id":"2210.11466","title":"Surgical Fine-Tuning Improves Adaptation to Distribution Shifts","created":"2022-10-20","cited_by_count":205},{"id":"1810.05934","title":"A System for Massively Parallel Hyperparameter Tuning","created":"2018-10-13","cited_by_count":202},{"id":"2102.10772","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","created":"2021-02-22","cited_by_count":195},{"id":"2002.02923","title":"Geometric Dataset Distances via Optimal Transport","created":"2020-02-07","cited_by_count":158},{"id":"2008.03156","title":"Better Fine-Tuning by Reducing Representational Collapse","created":"2020-08-06","cited_by_count":157},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148},{"id":"2003.03384","title":"AutoML-Zero: Evolving Machine Learning Algorithms From Scratch","created":"2020-03-06","cited_by_count":143},{"id":"1909.02950","title":"Supervised Multimodal Bitransformers for Classifying Images and Text","created":"2019-09-06","cited_by_count":130},{"id":"2205.14141","title":"Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation","created":"2022-05-27","cited_by_count":93},{"id":"2012.14176","title":"Deep Visual Domain Adaptation","created":"2020-12-28","cited_by_count":91},{"id":"2201.12122","title":"Can Wikipedia Help Offline Reinforcement Learning?","created":"2022-01-28","cited_by_count":77},{"id":"1906.09607","title":"Densely Connected Search Space for More Flexible Neural Architecture Search","created":"2019-06-23","cited_by_count":52},{"id":"2110.05668","title":"NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks","created":"2021-10-12","cited_by_count":32},{"id":"2008.01677","title":"Simultaneous Semantic Alignment Network for Heterogeneous Domain Adaptation","created":"2020-08-04","cited_by_count":21},{"id":"2103.15798","title":"Rethinking Neural Operations for Diverse Tasks","created":"2021-03-29","cited_by_count":18},{"id":"2204.07554","title":"Efficient Architecture Search for Diverse Tasks","created":"2022-04-15","cited_by_count":18},{"id":"1908.10552","title":"Heterogeneous Domain Adaptation via Soft Transfer Network","created":"2019-08-28","cited_by_count":14},{"id":"2011.00890","title":"Emergent Communication Pretraining for Few-Shot Machine Translation","created":"2020-11-02","cited_by_count":13},{"id":"2005.09862","title":"A Further Study of Unsupervised Pre-training for Transformer Based Speech Recognition","created":"2020-05-20","cited_by_count":12},{"id":"2301.02120","title":"Reprogramming Pretrained Language Models for Protein Sequence Representation Learning","created":"2023-01-05","cited_by_count":12},{"id":"1907.09500","title":"deepCR: Cosmic Ray Rejection with Deep Learning","created":"2019-07-22","cited_by_count":11},{"id":"2006.03645","title":"sEMG Gesture Recognition with a Simple Model of Attention","created":"2020-06-05","cited_by_count":10},{"id":"2107.12460","title":"Don't Sweep your Learning Rate under the Rug: A Closer Look at Cross-modal Transfer of Pretrained Transformers","created":"2021-07-26","cited_by_count":6}],"next_cursor":null}