{"list":"other","total":51,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"2107.03006","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","created":"2021-07-07","cited_by_count":1719},{"id":"1711.06396","title":"VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection","created":"2017-11-17","cited_by_count":1323},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"2107.00630","title":"Variational Diffusion Models","created":"2021-07-01","cited_by_count":1153},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648},{"id":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"2205.14987","title":"A Continuous Time Framework for Discrete Denoising Models","created":"2022-05-30","cited_by_count":451},{"id":"1902.06326","title":"PIXOR: Real-time 3D Object Detection from Point Clouds","created":"2019-02-17","cited_by_count":358},{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328},{"id":"2308.01898","title":"UniSim: A Neural Closed-Loop Sensor Simulator","created":"2023-08-03","cited_by_count":297},{"id":"1608.05859","title":"Using the Output Embedding to Improve Language Models","created":"2016-08-20","cited_by_count":272},{"id":"2111.14643","title":"Urban Radiance Fields","created":"2021-11-29","cited_by_count":263},{"id":"2104.10490","title":"FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras","created":"2021-04-21","cited_by_count":239},{"id":"2012.12395","title":"Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net","created":"2020-12-22","cited_by_count":228},{"id":"1909.11652","title":"Deep Dynamics Models for Learning Dexterous Manipulation","created":"2019-09-25","cited_by_count":206},{"id":"2008.05930","title":"Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations","created":"2020-08-13","cited_by_count":153},{"id":"2206.11894","title":"MaskViT: Masked Visual Pre-Training for Video Prediction","created":"2022-06-23","cited_by_count":114},{"id":"2305.04966","title":"NerfAcc: Efficient Sampling Accelerates NeRFs","created":"2023-05-08","cited_by_count":90},{"id":"2305.08842","title":"Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks","created":"2023-05-15","cited_by_count":82},{"id":"2209.04439","title":"Improved Masked Image Generation with Token-Critic","created":"2022-09-09","cited_by_count":64},{"id":"2110.04076","title":"Self-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networks","created":"2021-09-28","cited_by_count":42}],"next_cursor":null}