{"total":42,"rows":[{"id":"2402.01831","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","created":"2024-02-02","cited_by_count":186,"area":null},{"id":"2501.01108","title":"MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization","created":"2025-01-02","cited_by_count":68,"area":null},{"id":"2410.00872","title":"Do Music Generation Models Encode Music Theory?","created":"2024-10-01","cited_by_count":13,"area":null},{"id":"2409.06029","title":"SongCreator: Lyrics-based Universal Song Generation","created":"2024-09-09","cited_by_count":12,"area":null},{"id":"2410.15573","title":"OpenMU: Your Swiss Army Knife for Music Understanding","created":"2024-10-21","cited_by_count":9,"area":null},{"id":"2409.11264","title":"LC-Protonets: Multi-Label Few-Shot Learning for World Music Audio Tagging","created":"2024-09-17","cited_by_count":7,"area":null},{"id":"2505.16306","title":"Layer-wise Investigation of Large-Scale Self-Supervised Music Representation Models","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2502.12511","title":"Myna: Masking-Based Contrastive Learning of Musical Representations","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2506.17055","title":"Universal Music Representations? Evaluating Foundation Models on World Music Corpora","created":"2025-06-20","cited_by_count":3,"area":null},{"id":"2509.01588","title":"From Discord to Harmony: Decomposed Consonance-based Training for Improved Audio Chord Estimation","created":"2025-09-01","cited_by_count":3,"area":null},{"id":"2408.00674","title":"ChordSync: Conformer-Based Alignment of Chord Annotations to Music Audio","created":"2024-08-01","cited_by_count":2,"area":null},{"id":"2506.17818","title":"CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2506.23873","title":"Emergent musical properties of a transformer under contrastive self-supervised learning","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2603.11042","title":"V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2607.08168","title":"MuScriptor: An Open Model for Multi-Instrument Music Transcription","created":"2026-07-09","cited_by_count":2,"area":null},{"id":"2409.09378","title":"Prevailing Research Areas for Music AI in the Era of Foundation Models","created":"2024-09-14","cited_by_count":1,"area":null},{"id":"2502.12925","title":"Keep what you need : extracting efficient subnetworks from large audio representation models","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2512.17209","title":"Do Foundational Audio Encoders Understand Music Structure?","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2602.10058","title":"Evaluating Disentangled Representations for Controllable Music Generation","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2606.06444","title":"USAD 2.0: Scaling Representation Distillation for Universal Audio Understanding","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2409.06690","title":"Benchmarking Sub-Genre Classification For Mainstage Dance Music","created":"2024-09-10","cited_by_count":0,"area":null},{"id":"2505.10101","title":"LAV: Audio-Driven Dynamic Visual Generation with Neural Compression and StyleGAN2","created":"2025-05-15","cited_by_count":0,"area":null},{"id":"2505.17233","title":"Semantic-Aware Interpretable Multimodal Music Auto-Tagging","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2507.04776","title":"Improving BERT for Symbolic Music Understanding Using Token Denoising and Pianoroll Prediction","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2510.04688","title":"A Study on the Data Distribution Gap in Music Emotion Recognition","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2510.05756","title":"Transcribing Rhythmic Patterns of the Guitar Track in Polyphonic Music","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2511.18869","title":"Hear: Hierarchically Enhanced Aesthetic Representations For Multidimensional Music Evaluation","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2601.09603","title":"Linear Complexity Self-Supervised Learning for Music Understanding with Random Quantizer","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2603.03190","title":"Expectation and Acoustic Neural Network Representations Enhance Music Identification from Brain Activity","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.08759","title":"EDMFormer: Genre-Specific Self-Supervised Learning for Music Structure Segmentation","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2603.27218","title":"Unsupervised Evaluation of Deep Audio Embeddings for Music Structure Analysis","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2603.27237","title":"Can pre-trained Deep Learning models predict groove ratings?","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2604.10021","title":"Masked Contrastive Pre-Training Improves Music Audio Key Detection","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2604.20847","title":"Revisiting Content-Based Music Recommendation: Efficient Feature Aggregation from Large-Scale Music Models","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2605.00371","title":"GaMMA: Towards Joint Global-Temporal Music Understanding in Large Multimodal Models","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2606.00125","title":"Multimodal Music Recommendation System using LLMs","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.05198","title":"Noisy-Channel Minimum Bayes Risk Decoding","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.06165","title":"Audio-to-Score Transcription using Pre-trained Features, Data Augmentation, and the New SheetSage-A2S Dataset","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.14819","title":"What Makes a Good Layer? Assessing the Layer-Wise Intrinsic Properties of Music Foundation Models","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.25621","title":"Dissonance Spectrum explicitly models perceptual frequency interactions for better music understanding","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.30974","title":"CoJEPA: Combining Contrastive Learning and JEPA for Global-Local Music Representations","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2610.15957","title":"Harmonic Representations in Symbolic Music Transformers are Localized and Controllable","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}