{"list":"other","total":89,"rows":[{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"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":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"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":"1905.06316","title":"What do you learn from context? Probing for sentence structure in contextualized word representations","created":"2019-05-15","cited_by_count":438},{"id":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431},{"id":"2306.06546","title":"High-Fidelity Audio Compression with Improved RVQGAN","created":"2023-06-11","cited_by_count":431},{"id":"1812.08466","title":"Fr\\'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms","created":"2018-12-20","cited_by_count":225},{"id":"1612.01840","title":"FMA: A Dataset For Music Analysis","created":"2016-12-06","cited_by_count":207},{"id":"2302.04222","title":"Glaze: Protecting Artists from Style Mimicry by Text-to-Image Models","created":"2023-02-08","cited_by_count":205},{"id":"2306.00107","title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","created":"2023-05-31","cited_by_count":181},{"id":"2206.03208","title":"From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation","created":"2022-06-07","cited_by_count":141},{"id":"2211.08553","title":"Hybrid Transformers for Music Source Separation","created":"2022-11-15","cited_by_count":134},{"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":"2109.06129","title":"Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color","created":"2021-09-13","cited_by_count":119},{"id":"2206.03761","title":"A Survey on the Fairness of Recommender Systems","created":"2022-06-08","cited_by_count":102},{"id":"2311.08355","title":"Mustango: Toward Controllable Text-to-Music Generation","created":"2023-11-14","cited_by_count":100},{"id":"1911.13254","title":"Music Source Separation in the Waveform Domain","created":"2019-11-27","cited_by_count":99},{"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":"2307.16372","title":"LP-MusicCaps: LLM-Based Pseudo Music Captioning","created":"2023-07-31","cited_by_count":83},{"id":"2311.07069","title":"Music ControlNet: Multiple Time-varying Controls for Music Generation","created":"2023-11-13","cited_by_count":83},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78},{"id":"2301.11757","title":"Mo\\^usai: Text-to-Music Generation with Long-Context Latent Diffusion","created":"2023-01-27","cited_by_count":78},{"id":"2401.17264","title":"Proactive Detection of Voice Cloning with Localized Watermarking","created":"2024-01-30","cited_by_count":78},{"id":"2310.13828","title":"Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models","created":"2023-10-20","cited_by_count":75},{"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":"2209.15174","title":"Music Source Separation with Band-split RNN","created":"2022-09-30","cited_by_count":70},{"id":"2107.05677","title":"Codified audio language modeling learns useful representations for music information retrieval","created":"2021-07-12","cited_by_count":64},{"id":"2307.04686","title":"VampNet: Music Generation via Masked Acoustic Token Modeling","created":"2023-07-10","cited_by_count":57},{"id":"2011.06801","title":"A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions","created":"2020-11-13","cited_by_count":56},{"id":"2402.14285","title":"Symbolic Music Generation with Non-Differentiable Rule Guided Diffusion","created":"2024-02-22","cited_by_count":54},{"id":"2306.00110","title":"MuseCoco: Generating Symbolic Music from Text","created":"2023-05-31","cited_by_count":52},{"id":"2308.12770","title":"WavMark: Watermarking for Audio Generation","created":"2023-08-24","cited_by_count":50},{"id":"2404.11343","title":"Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System","created":"2024-04-17","cited_by_count":50},{"id":"2311.03318","title":"A Foundation Model for Music Informatics","created":"2023-11-06","cited_by_count":46},{"id":"2309.08730","title":"MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response","created":"2023-09-15","cited_by_count":45},{"id":"2408.01337","title":"MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models","created":"2024-08-02","cited_by_count":44},{"id":"2306.10548","title":"MARBLE: Music Audio Representation Benchmark for Universal Evaluation","created":"2023-06-18","cited_by_count":38},{"id":"2008.01951","title":"MusPy: A Toolkit for Symbolic Music Generation","created":"2020-08-05","cited_by_count":37},{"id":"2311.00968","title":"Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model","created":"2023-11-02","cited_by_count":37},{"id":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37},{"id":"2402.06178","title":"MusicMagus: Zero-Shot Text-to-Music Editing via Diffusion Models","created":"2024-02-09","cited_by_count":32},{"id":"1812.04186","title":"A Functional Taxonomy of Music Generation Systems","created":"2018-12-11","cited_by_count":31},{"id":"1906.04972","title":"Toward Interpretable Music Tagging with Self-Attention","created":"2019-06-12","cited_by_count":30},{"id":"2308.12241","title":"LLMRec: Benchmarking Large Language Models on Recommendation Task","created":"2023-08-23","cited_by_count":30},{"id":"2203.09893","title":"A Lightweight Instrument-Agnostic Model for Polyphonic Note Transcription and Multipitch Estimation","created":"2022-03-18","cited_by_count":28},{"id":"2010.10291","title":"Automatic multitrack mixing with a differentiable mixing console of neural audio effects","created":"2020-10-20","cited_by_count":27},{"id":"2110.07468","title":"SingGAN: Generative Adversarial Network For High-Fidelity Singing Voice Generation","created":"2021-10-14","cited_by_count":27},{"id":"2104.11984","title":"MusCaps: Generating Captions for Music Audio","created":"2021-04-24","cited_by_count":23},{"id":"1812.04832","title":"MorpheuS: generating structured music with constrained patterns and tension","created":"2018-12-12","cited_by_count":22},{"id":"2406.02255","title":"MidiCaps: A large-scale MIDI dataset with text captions","created":"2024-06-04","cited_by_count":19},{"id":"1811.00334","title":"Deep Learning for Tube Amplifier Emulation","created":"2018-11-01","cited_by_count":18},{"id":"2005.07788","title":"Reliable Local Explanations for Machine Listening","created":"2020-05-15","cited_by_count":18},{"id":"2305.06594","title":"V2Meow: Meowing to the Visual Beat via Video-to-Music Generation","created":"2023-05-11","cited_by_count":18},{"id":"2309.02265","title":"PESTO: Pitch Estimation with Self-supervised Transposition-equivariant Objective","created":"2023-09-05","cited_by_count":18},{"id":"2104.13056","title":"Generating Lead Sheets with Affect: A Novel Conditional seq2seq Framework","created":"2021-04-27","cited_by_count":17},{"id":"2209.00130","title":"Evaluating generative audio systems and their metrics","created":"2022-08-31","cited_by_count":16},{"id":"2402.16998","title":"What Do Language Models Hear? Probing for Auditory Representations in Language Models","created":"2024-02-26","cited_by_count":15},{"id":"2405.18386","title":"Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuning","created":"2024-05-28","cited_by_count":15},{"id":"2304.11029","title":"CLaMP: Contrastive Language-Music Pre-training for Cross-Modal Symbolic Music Information Retrieval","created":"2023-04-21","cited_by_count":14},{"id":"2401.14542","title":"Exploring Musical Roots: Applying Audio Embeddings to Empower Influence Attribution for a Generative Music Model","created":"2024-01-25","cited_by_count":13},{"id":"2208.12485","title":"Concept-Based Techniques for \"Musicologist-friendly\" Explanations in a Deep Music Classifier","created":"2022-08-26","cited_by_count":12},{"id":"1810.05246","title":"Piano Genie","created":"2018-10-11","cited_by_count":11},{"id":"2208.11428","title":"Automatic music mixing with deep learning and out-of-domain data","created":"2022-08-24","cited_by_count":11},{"id":"2111.09931","title":"DawDreamer: Bridging the Gap Between Digital Audio Workstations and Python Interfaces","created":"2021-11-18","cited_by_count":10},{"id":"2402.17467","title":"Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey","created":"2024-02-27","cited_by_count":10},{"id":"2407.14364","title":"Towards Assessing Data Replication in Music Generation with Music Similarity Metrics on Raw Audio","created":"2024-07-19","cited_by_count":10},{"id":"2311.02171","title":"Emergence of Abstract State Representations in Embodied Sequence Modeling","created":"2023-11-03","cited_by_count":9},{"id":"2111.11636","title":"Music Classification: Beyond Supervised Learning, Towards Real-world Applications","created":"2021-11-23","cited_by_count":7},{"id":"2310.00140","title":"GASS: Generalizing Audio Source Separation with Large-scale Data","created":"2023-09-29","cited_by_count":6},{"id":"2107.13634","title":"Don't Separate, Learn to Remix: End-to-End Neural Remixing with Joint Optimization","created":"2021-07-28","cited_by_count":5},{"id":"2409.08795","title":"LLaQo: Towards a Query-Based Coach in Expressive Music Performance Assessment","created":"2024-09-13","cited_by_count":5},{"id":"2009.02051","title":"Towards Musically Meaningful Explanations Using Source Separation","created":"2020-09-04","cited_by_count":4},{"id":"2307.07426","title":"Real-time Percussive Technique Recognition and Embedding Learning for the Acoustic Guitar","created":"2023-07-13","cited_by_count":3},{"id":"1607.02444","title":"Explaining Deep Convolutional Neural Networks on Music Classification","created":"2016-07-08","cited_by_count":2},{"id":"2106.11054","title":"Visual Probing: Cognitive Framework for Explaining Self-Supervised Image Representations","created":"2021-06-21","cited_by_count":2}],"next_cursor":null}