{"list":"other","total":69,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"2108.02938","title":"ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models","created":"2021-08-06","cited_by_count":635},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"2004.05498","title":"FDA: Fourier Domain Adaptation for Semantic Segmentation","created":"2020-04-11","cited_by_count":541},{"id":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488},{"id":"2111.15640","title":"Diffusion Autoencoders: Toward a Meaningful and Decodable Representation","created":"2021-11-30","cited_by_count":449},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448},{"id":"2306.06546","title":"High-Fidelity Audio Compression with Improved RVQGAN","created":"2023-06-11","cited_by_count":431},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347},{"id":"1602.02282","title":"Ladder Variational Autoencoders","created":"2016-02-06","cited_by_count":318},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273},{"id":"2107.00645","title":"Global Filter Networks for Image Classification","created":"2021-07-01","cited_by_count":260},{"id":"2207.09983","title":"Diffsound: Discrete Diffusion Model for Text-to-sound Generation","created":"2022-07-20","cited_by_count":257},{"id":"2206.04658","title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","created":"2022-06-09","cited_by_count":251},{"id":"2111.13587","title":"Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers","created":"2021-11-24","cited_by_count":248},{"id":"1812.08466","title":"Fr\\'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms","created":"2018-12-20","cited_by_count":225},{"id":"1810.12247","title":"Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset","created":"2018-10-29","cited_by_count":217},{"id":"2407.14358","title":"Stable Audio Open","created":"2024-07-19","cited_by_count":197},{"id":"2105.14576","title":"StyTr$^2$: Image Style Transfer with Transformers","created":"2021-05-30","cited_by_count":187},{"id":"2302.03917","title":"Noise2Music: Text-conditioned Music Generation with Diffusion Models","created":"2023-02-08","cited_by_count":173},{"id":"1806.03185","title":"Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation","created":"2018-06-08","cited_by_count":125},{"id":"2305.09636","title":"SoundStorm: Efficient Parallel Audio Generation","created":"2023-05-16","cited_by_count":114},{"id":"2308.01546","title":"MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies","created":"2023-08-03","cited_by_count":94},{"id":"1312.5851","title":"Fast Training of Convolutional Networks through FFTs","created":"2013-12-20","cited_by_count":89},{"id":"2311.07069","title":"Music ControlNet: Multiple Time-varying Controls for Music Generation","created":"2023-11-13","cited_by_count":83},{"id":"2111.05011","title":"RAVE: A variational autoencoder for fast and high-quality neural audio synthesis","created":"2021-11-09","cited_by_count":73},{"id":"2401.12179","title":"DITTO: Diffusion Inference-Time T-Optimization for Music Generation","created":"2024-01-22","cited_by_count":73},{"id":"1611.05013","title":"PixelVAE: A Latent Variable Model for Natural Images","created":"2016-11-15","cited_by_count":70},{"id":"2307.04686","title":"VampNet: Music Generation via Masked Acoustic Token Modeling","created":"2023-07-10","cited_by_count":57},{"id":"1708.08917","title":"CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices","created":"2017-08-29","cited_by_count":55},{"id":"2203.12198","title":"Deep Frequency Filtering for Domain Generalization","created":"2022-03-23","cited_by_count":43},{"id":"2011.04823","title":"Language Through a Prism: A Spectral Approach for Multiscale Language Representations","created":"2020-11-09","cited_by_count":39},{"id":"1811.09620","title":"TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer","created":"2018-11-22","cited_by_count":33},{"id":"2408.06500","title":"Music2Latent: Consistency Autoencoders for Latent Audio Compression","created":"2024-08-12","cited_by_count":33},{"id":"2312.08723","title":"StemGen: A music generation model that listens","created":"2023-12-14","cited_by_count":32},{"id":"2311.00613","title":"Controllable Music Production with Diffusion Models and Guidance Gradients","created":"2023-11-01","cited_by_count":29},{"id":"1702.08396","title":"Learning Hierarchical Features from Generative Models","created":"2017-02-27","cited_by_count":27},{"id":"2412.08550","title":"Sketch2Sound: Controllable Audio Generation via Time-Varying Signals and Sonic Imitations","created":"2024-12-11","cited_by_count":24},{"id":"2411.07126","title":"Edify Image: High-Quality Image Generation with Pixel Space Laplacian Diffusion Models","created":"2024-11-11","cited_by_count":23},{"id":"2308.02560","title":"From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion","created":"2023-08-02","cited_by_count":22},{"id":"2305.15099","title":"Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator","created":"2023-05-24","cited_by_count":20},{"id":"1803.06841","title":"Music Style Transfer: A Position Paper","created":"2018-03-19","cited_by_count":16},{"id":"2403.18636","title":"A Diffusion-Based Generative Equalizer for Music Restoration","created":"2024-03-27","cited_by_count":12},{"id":"2408.09027","title":"Efficient Autoregressive Audio Modeling via Next-Scale Prediction","created":"2024-08-16","cited_by_count":11},{"id":"2402.13763","title":"Music Style Transfer with Time-Varying Inversion of Diffusion Models","created":"2024-02-21","cited_by_count":10},{"id":"1612.04739","title":"An Architecture for Deep, Hierarchical Generative Models","created":"2016-12-08","cited_by_count":6},{"id":"2407.05471","title":"Fine-Grained and Interpretable Neural Speech Editing","created":"2024-07-07","cited_by_count":6},{"id":"2408.09792","title":"Unsupervised Composable Representations for Audio","created":"2024-08-19","cited_by_count":4},{"id":"2502.12759","title":"High-Fidelity Music Vocoder using Neural Audio Codecs","created":"2025-02-18","cited_by_count":3},{"id":"2406.19328","title":"Subtractive Training for Music Stem Insertion using Latent Diffusion Models","created":"2024-06-27","cited_by_count":2},{"id":"2407.04379","title":"A Mapping Strategy for Interacting with Latent Audio Synthesis Using Artistic Materials","created":"2024-07-05","cited_by_count":2},{"id":"2501.05050","title":"Music Tagging with Classifier Group Chains","created":"2025-01-09","cited_by_count":2},{"id":"2409.13589","title":"Analyzing the Effect of $k$-Space Features in MRI Classification Models","created":"2024-09-20","cited_by_count":1}],"next_cursor":null}