{"list":"other","total":128,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"2106.13008","title":"Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting","created":"2021-06-24","cited_by_count":1676},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2205.13504","title":"Are Transformers Effective for Time Series Forecasting?","created":"2022-05-26","cited_by_count":1424},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"1607.01759","title":"Bag of Tricks for Efficient Text Classification","created":"2016-07-06","cited_by_count":876},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1606.07792","title":"Wide & Deep Learning for Recommender Systems","created":"2016-06-24","cited_by_count":747},{"id":"1603.06560","title":"Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization","created":"2016-03-21","cited_by_count":699},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"1703.04247","title":"DeepFM: A Factorization-Machine based Neural Network for CTR Prediction","created":"2017-03-13","cited_by_count":676},{"id":"1809.11165","title":"GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration","created":"2018-09-28","cited_by_count":609},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"1706.06978","title":"Deep Interest Network for Click-Through Rate Prediction","created":"2017-06-21","cited_by_count":544},{"id":"1807.01774","title":"BOHB: Robust and Efficient Hyperparameter Optimization at Scale","created":"2018-07-04","cited_by_count":470},{"id":"2004.13408","title":"Time Series Forecasting With Deep Learning: A Survey","created":"2020-04-28","cited_by_count":459},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"2001.00326","title":"NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search","created":"2020-01-02","cited_by_count":416},{"id":"1807.05118","title":"Tune: A Research Platform for Distributed Model Selection and Training","created":"2018-07-13","cited_by_count":395},{"id":"1703.01041","title":"Large-Scale Evolution of Image Classifiers","created":"2017-03-03","cited_by_count":348},{"id":"1311.0776","title":"The Composition Theorem for Differential Privacy","created":"2013-11-04","cited_by_count":297},{"id":"1502.05700","title":"Scalable Bayesian Optimization Using Deep Neural Networks","created":"2015-02-19","cited_by_count":284},{"id":"1611.02167","title":"Designing Neural Network Architectures using Reinforcement Learning","created":"2016-11-07","cited_by_count":279},{"id":"1910.04465","title":"Searching for A Robust Neural Architecture in Four GPU Hours","created":"2019-10-10","cited_by_count":260},{"id":"1902.07638","title":"Random Search and Reproducibility for Neural Architecture Search","created":"2019-02-20","cited_by_count":254},{"id":"2207.10666","title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","created":"2022-07-21","cited_by_count":234},{"id":"2106.03348","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","created":"2021-06-07","cited_by_count":216},{"id":"1901.11117","title":"The Evolved Transformer","created":"2019-01-30","cited_by_count":180},{"id":"2208.03987","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","created":"2022-08-08","cited_by_count":149},{"id":"2202.10108","title":"ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond","created":"2022-02-21","cited_by_count":117},{"id":"1505.08052","title":"Batch Bayesian Optimization via Local Penalization","created":"2015-05-29","cited_by_count":104},{"id":"1411.2664","title":"Preserving Statistical Validity in Adaptive Data Analysis","created":"2014-11-10","cited_by_count":103},{"id":"2010.11430","title":"Self-training and Pre-training are Complementary for Speech Recognition","created":"2020-10-22","cited_by_count":99},{"id":"2210.04284","title":"SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters","created":"2022-10-09","cited_by_count":83},{"id":"2203.12533","title":"Pathways: Asynchronous Distributed Dataflow for ML","created":"2022-03-23","cited_by_count":82},{"id":"2208.13753","title":"Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis","created":"2022-08-29","cited_by_count":75},{"id":"2211.10772","title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting","created":"2022-11-19","cited_by_count":74},{"id":"1910.05733","title":"One-Shot Neural Architecture Search via Self-Evaluated Template Network","created":"2019-10-13","cited_by_count":69},{"id":"2104.14222","title":"Privacy-Preserving Portrait Matting","created":"2021-04-29","cited_by_count":60},{"id":"2003.07449","title":"Object-Centric Image Generation from Layouts","created":"2020-03-16","cited_by_count":57},{"id":"2211.14108","title":"3DDesigner: Towards Photorealistic 3D Object Generation and Editing with Text-guided Diffusion Models","created":"2022-11-25","cited_by_count":57},{"id":"2012.14583","title":"Understanding and Improving Lexical Choice in Non-Autoregressive Translation","created":"2020-12-29","cited_by_count":56},{"id":"2201.01976","title":"SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection","created":"2022-01-06","cited_by_count":52},{"id":"2207.04491","title":"DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer","created":"2022-07-10","cited_by_count":50},{"id":"2003.11571","title":"Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis","created":"2020-03-25","cited_by_count":49},{"id":"2202.08088","title":"Latent Outlier Exposure for Anomaly Detection with Contaminated Data","created":"2022-02-16","cited_by_count":48},{"id":"2206.00423","title":"Open-environment Machine Learning","created":"2022-06-01","cited_by_count":48},{"id":"2205.15308","title":"Parameter-Efficient and Student-Friendly Knowledge Distillation","created":"2022-05-28","cited_by_count":47},{"id":"2206.00923","title":"Modeling Image Composition for Complex Scene Generation","created":"2022-06-02","cited_by_count":43},{"id":"1706.09138","title":"Perceptual Adversarial Networks for Image-to-Image Transformation","created":"2017-06-28","cited_by_count":42},{"id":"1803.00657","title":"Evolutionary Generative Adversarial Networks","created":"2018-03-01","cited_by_count":42},{"id":"2010.02693","title":"SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Filling","created":"2020-10-06","cited_by_count":42},{"id":"2211.14842","title":"Unified Discrete Diffusion for Simultaneous Vision-Language Generation","created":"2022-11-27","cited_by_count":39},{"id":"1904.01206","title":"Progressive LiDAR Adaptation for Road Detection","created":"2019-04-02","cited_by_count":37},{"id":"2010.06176","title":"ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding","created":"2020-10-13","cited_by_count":36},{"id":"2112.02582","title":"PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation","created":"2021-12-05","cited_by_count":36},{"id":"2208.12256","title":"Masked Autoencoders Enable Efficient Knowledge Distillers","created":"2022-08-25","cited_by_count":36},{"id":"2106.00903","title":"Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation","created":"2021-06-02","cited_by_count":34},{"id":"2203.09507","title":"Towards Data-Efficient Detection Transformers","created":"2022-03-17","cited_by_count":34},{"id":"2205.14354","title":"Multi-Task Learning with Multi-Query Transformer for Dense Prediction","created":"2022-05-28","cited_by_count":34},{"id":"2101.05273","title":"AutoDS: Towards Human-Centered Automation of Data Science","created":"2021-01-13","cited_by_count":32},{"id":"2105.06458","title":"High-Resolution Complex Scene Synthesis with Transformers","created":"2021-05-13","cited_by_count":31},{"id":"2208.10160","title":"PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation","created":"2022-08-22","cited_by_count":31}],"next_cursor":"100"}