{"list":"other","total":97,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"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":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"2106.10689","title":"NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction","created":"2021-06-20","cited_by_count":1712},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1198},{"id":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"id":"1410.8516","title":"NICE: Non-linear Independent Components Estimation","created":"2014-10-30","cited_by_count":1058},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"1601.06759","title":"Pixel Recurrent Neural Networks","created":"2016-01-25","cited_by_count":816},{"id":"2011.13084","title":"Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes","created":"2020-11-26","cited_by_count":751},{"id":"2102.13090","title":"IBRNet: Learning Multi-View Image-Based Rendering","created":"2021-02-25","cited_by_count":703},{"id":"2104.10078","title":"UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction","created":"2021-04-20","cited_by_count":646},{"id":"2012.15838","title":"Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans","created":"2020-12-31","cited_by_count":634},{"id":"1710.07035","title":"Generative Adversarial Networks: An Overview","created":"2017-10-19","cited_by_count":590},{"id":"1912.10211","title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","created":"2019-12-21","cited_by_count":574},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1703.10135","title":"Tacotron: Towards End-to-End Speech Synthesis","created":"2017-03-29","cited_by_count":490},{"id":"1710.11248","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","created":"2017-10-30","cited_by_count":490},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"1508.06576","title":"A Neural Algorithm of Artistic Style","created":"2015-08-26","cited_by_count":483},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447},{"id":"1701.05517","title":"PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications","created":"2017-01-19","cited_by_count":417},{"id":"1910.06711","title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","created":"2019-10-08","cited_by_count":354},{"id":"1910.11480","title":"Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram","created":"2019-10-25","cited_by_count":340},{"id":"1811.00002","title":"WaveGlow: A Flow-based Generative Network for Speech Synthesis","created":"2018-10-31","cited_by_count":309},{"id":"2110.01691","title":"AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts","created":"2021-10-04","cited_by_count":268},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"2103.16507","title":"PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop","created":"2021-03-30","cited_by_count":250},{"id":"2008.05511","title":"Free View Synthesis","created":"2020-08-12","cited_by_count":231},{"id":"2103.05606","title":"NeX: Real-time View Synthesis with Neural Basis Expansion","created":"2021-03-09","cited_by_count":216},{"id":"1905.01235","title":"Scaling and Benchmarking Self-Supervised Visual Representation Learning","created":"2019-05-03","cited_by_count":201},{"id":"1910.12638","title":"Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders","created":"2019-10-25","cited_by_count":198},{"id":"2102.10772","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","created":"2021-02-22","cited_by_count":195},{"id":"2010.10915","title":"Contrastive Learning of General-Purpose Audio Representations","created":"2020-10-21","cited_by_count":169},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168},{"id":"2104.01409","title":"Diff-TTS: A Denoising Diffusion Model for Text-to-Speech","created":"2021-04-03","cited_by_count":157},{"id":"1709.06298","title":"MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment","created":"2017-09-19","cited_by_count":151},{"id":"1803.05428","title":"A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music","created":"2018-03-13","cited_by_count":131},{"id":"1612.07837","title":"SampleRNN: An Unconditional End-to-End Neural Audio Generation Model","created":"2016-12-22","cited_by_count":110},{"id":"1810.11846","title":"LPCNet: Improving Neural Speech Synthesis Through Linear Prediction","created":"2018-10-28","cited_by_count":110},{"id":"2103.11571","title":"Neural Lumigraph Rendering","created":"2021-03-22","cited_by_count":105},{"id":"2103.00993","title":"AdaSpeech: Adaptive Text to Speech for Custom Voice","created":"2021-03-01","cited_by_count":98},{"id":"1706.07068","title":"CAN: Creative Adversarial Networks, Generating \"Art\" by Learning About Styles and Deviating from Style Norms","created":"2017-06-21","cited_by_count":96},{"id":"1804.06023","title":"DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor","created":"2018-04-17","cited_by_count":95},{"id":"1810.07217","title":"Hierarchical Generative Modeling for Controllable Speech Synthesis","created":"2018-10-16","cited_by_count":93},{"id":"1612.01010","title":"DeepBach: a Steerable Model for Bach Chorales Generation","created":"2016-12-03","cited_by_count":91},{"id":"1807.06358","title":"IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis","created":"2018-07-17","cited_by_count":85},{"id":"2103.09410","title":"Contrastive Learning of Musical Representations","created":"2021-03-17","cited_by_count":82},{"id":"2008.08474","title":"Human Body Model Fitting by Learned Gradient Descent","created":"2020-08-19","cited_by_count":81},{"id":"2003.14323","title":"How Useful is Self-Supervised Pretraining for Visual Tasks?","created":"2020-03-31","cited_by_count":80},{"id":"2106.06406","title":"PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior","created":"2021-06-11","cited_by_count":80},{"id":"1912.01679","title":"Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition","created":"2019-12-03","cited_by_count":66},{"id":"2109.09913","title":"Physics-based Human Motion Estimation and Synthesis from Videos","created":"2021-09-21","cited_by_count":66},{"id":"1605.07008","title":"madmom: a new Python Audio and Music Signal Processing Library","created":"2016-05-23","cited_by_count":64},{"id":"1806.10474","title":"The challenge of realistic music generation: modelling raw audio at scale","created":"2018-06-26","cited_by_count":63},{"id":"1812.04342","title":"Learning latent representations for style control and transfer in end-to-end speech synthesis","created":"2018-12-11","cited_by_count":61},{"id":"2111.12124","title":"Towards Learning Universal Audio Representations","created":"2021-11-23","cited_by_count":51},{"id":"1909.06654","title":"musicnn: Pre-trained convolutional neural networks for music audio tagging","created":"2019-09-14","cited_by_count":50},{"id":"2207.04630","title":"On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligence","created":"2022-07-11","cited_by_count":50},{"id":"2002.12625","title":"4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras","created":"2020-02-28","cited_by_count":49},{"id":"1906.01083","title":"MelNet: A Generative Model for Audio in the Frequency Domain","created":"2019-06-04","cited_by_count":42},{"id":"2101.12059","title":"VX2TEXT: End-to-End Learning of Video-Based Text Generation From Multimodal Inputs","created":"2021-01-28","cited_by_count":42},{"id":"1909.01700","title":"DurIAN: Duration Informed Attention Network For Multimodal Synthesis","created":"2019-09-04","cited_by_count":33},{"id":"2012.07267","title":"Multi-SpectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Combination for Speech Synthesis","created":"2020-12-14","cited_by_count":28},{"id":"2106.13871","title":"Transflower: probabilistic autoregressive dance generation with multimodal attention","created":"2021-06-25","cited_by_count":22},{"id":"2102.03229","title":"Multi-Task Self-Supervised Pre-Training for Music Classification","created":"2021-02-05","cited_by_count":18},{"id":"1712.05274","title":"A Hierarchical Recurrent Neural Network for Symbolic Melody Generation","created":"2017-12-14","cited_by_count":14},{"id":"2008.05289","title":"Speaker Conditional WaveRNN: Towards Universal Neural Vocoder for Unseen Speaker and Recording Conditions","created":"2020-08-09","cited_by_count":14},{"id":"2207.09193","title":"NDF: Neural Deformable Fields for Dynamic Human Modelling","created":"2022-07-19","cited_by_count":14},{"id":"2112.04214","title":"Learning music audio representations via weak language supervision","created":"2021-12-08","cited_by_count":13},{"id":"2203.09129","title":"Contrastive Learning with Positive-Negative Frame Mask for Music Representation","created":"2022-03-17","cited_by_count":10},{"id":"2008.09960","title":"Translating Paintings Into Music Using Neural Networks","created":"2020-08-23","cited_by_count":1}],"next_cursor":null}