{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448},{"id":"2106.06909","title":"GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio","created":"2021-06-13","cited_by_count":399},{"id":"2308.05734","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","created":"2023-08-10","cited_by_count":344},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267},{"id":"1612.01840","title":"FMA: A Dataset For Music Analysis","created":"2016-12-06","cited_by_count":207},{"id":"2402.04825","title":"Fast Timing-Conditioned Latent Audio Diffusion","created":"2024-02-07","cited_by_count":181},{"id":"2010.10915","title":"Contrastive Learning of General-Purpose Audio Representations","created":"2020-10-21","cited_by_count":169},{"id":"2311.01616","title":"Adapting Frechet Audio Distance for Generative Music Evaluation","created":"2023-11-02","cited_by_count":92},{"id":"1904.03416","title":"Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks","created":"2019-04-06","cited_by_count":87},{"id":"2208.12415","title":"MuLan: A Joint Embedding of Music Audio and Natural Language","created":"2022-08-26","cited_by_count":87},{"id":"1909.08494","title":"Cutting Music Source Separation Some Slakh: A Dataset to Study the Impact of Training Data Quality and Quantity","created":"2019-09-18","cited_by_count":86},{"id":"2304.00830","title":"AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models","created":"2023-04-03","cited_by_count":83},{"id":"2103.09410","title":"Contrastive Learning of Musical Representations","created":"2021-03-17","cited_by_count":82},{"id":"2301.11757","title":"Mo\\^usai: Text-to-Music Generation with Long-Context Latent Diffusion","created":"2023-01-27","cited_by_count":78},{"id":"2402.16153","title":"ChatMusician: Understanding and Generating Music Intrinsically with LLM","created":"2024-02-25","cited_by_count":68},{"id":"2302.02257","title":"Multi-Source Diffusion Models for Simultaneous Music Generation and Separation","created":"2023-02-04","cited_by_count":63},{"id":"2307.04686","title":"VampNet: Music Generation via Masked Acoustic Token Modeling","created":"2023-07-10","cited_by_count":57},{"id":"2301.12662","title":"SingSong: Generating musical accompaniments from singing","created":"2023-01-30","cited_by_count":55},{"id":"1711.02209","title":"Unsupervised Learning of Semantic Audio Representations","created":"2017-11-06","cited_by_count":44},{"id":"2307.15913","title":"Moisesdb: A dataset for source separation beyond 4-stems","created":"2023-07-29","cited_by_count":39},{"id":"2002.07942","title":"Source Separation with Deep Generative Priors","created":"2020-02-19","cited_by_count":36},{"id":"2208.12208","title":"Contrastive Audio-Language Learning for Music","created":"2022-08-25","cited_by_count":33},{"id":"2112.09312","title":"MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling","created":"2021-12-17","cited_by_count":32},{"id":"2312.08723","title":"StemGen: A music generation model that listens","created":"2023-12-14","cited_by_count":32},{"id":"2010.09542","title":"CLAR: Contrastive Learning of Auditory Representations","created":"2020-10-19","cited_by_count":31},{"id":"2308.14360","title":"InstructME: An Instruction Guided Music Edit And Remix Framework with Latent Diffusion Models","created":"2023-08-28","cited_by_count":23},{"id":"2102.03229","title":"Multi-Task Self-Supervised Pre-Training for Music Classification","created":"2021-02-05","cited_by_count":18},{"id":"2006.08386","title":"COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations","created":"2020-06-15","cited_by_count":13},{"id":"2112.04214","title":"Learning music audio representations via weak language supervision","created":"2021-12-08","cited_by_count":13},{"id":"2403.11706","title":"Generalized Multi-Source Inference for Text Conditioned Music Diffusion Models","created":"2024-03-18","cited_by_count":13},{"id":"2301.08562","title":"Latent Autoregressive Source Separation","created":"2023-01-09","cited_by_count":12},{"id":"2204.09079","title":"Music Source Separation with Generative Flow","created":"2022-04-19","cited_by_count":10},{"id":"2209.14458","title":"The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling","created":"2022-09-28","cited_by_count":10},{"id":"2008.02011","title":"Neural Loop Combiner: Neural Network Models for Assessing the Compatibility of Loops","created":"2020-08-05","cited_by_count":8},{"id":"2208.01141","title":"SampleMatch: Drum Sample Retrieval by Musical Context","created":"2022-08-01","cited_by_count":8},{"id":"2103.14208","title":"Modeling the Compatibility of Stem Tracks to Generate Music Mashups","created":"2021-03-26","cited_by_count":5},{"id":"2302.07077","title":"Multi-Source Contrastive Learning from Musical Audio","created":"2023-02-14","cited_by_count":4}],"next_cursor":null}