{"total":20,"rows":[{"id":"2401.03497","title":"EAT: Self-Supervised Pre-Training with Efficient Audio Transformer","created":"2024-01-07","cited_by_count":53,"area":null},{"id":"2406.16148","title":"Towards Open Respiratory Acoustic Foundation Models: Pretraining and Benchmarking","created":"2024-06-23","cited_by_count":23,"area":null},{"id":"2506.12285","title":"CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following","created":"2025-06-14","cited_by_count":17,"area":null},{"id":"2309.14580","title":"CWCL: Cross-Modal Transfer with Continuously Weighted Contrastive Loss","created":"2023-09-26","cited_by_count":12,"area":null},{"id":"2408.02514","title":"Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation","created":"2024-08-05","cited_by_count":8,"area":null},{"id":"2312.11234","title":"Perceptual Musical Features for Interpretable Audio Tagging","created":"2023-12-18","cited_by_count":7,"area":null},{"id":"2312.15190","title":"SAIC: Integration of Speech Anonymization and Identity Classification","created":"2023-12-23","cited_by_count":7,"area":null},{"id":"2506.18843","title":"USAD: Universal Speech and Audio Representation via Distillation","created":"2025-06-23","cited_by_count":7,"area":null},{"id":"2508.12709","title":"MATPAC++: Enhanced Masked Latent Prediction for Self-Supervised Audio Representation Learning","created":"2025-08-18","cited_by_count":6,"area":null},{"id":"2405.08679","title":"Investigating Design Choices in Joint-Embedding Predictive Architectures for General Audio Representation Learning","created":"2024-05-14","cited_by_count":4,"area":null},{"id":"2502.12031","title":"Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2301.12058","title":"Aerial Image Object Detection With Vision Transformer Detector (ViTDet)","created":"2023-01-28","cited_by_count":3,"area":null},{"id":"2401.08415","title":"From Coarse to Fine: Efficient Training for Audio Spectrogram Transformers","created":"2024-01-16","cited_by_count":1,"area":null},{"id":"2503.16311","title":"Structured-Noise Masked Modeling for Video, Audio and Beyond","created":"2025-03-20","cited_by_count":1,"area":null},{"id":"2509.18424","title":"Scattering Transformer: A Training-Free Transformer Architecture for Heart Murmur Detection","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2403.09579","title":"uaMix-MAE: Efficient Tuning of Pretrained Audio Transformers with Unsupervised Audio Mixtures","created":"2024-03-14","cited_by_count":0,"area":null},{"id":"2411.19806","title":"Zero-shot Musical Stem Retrieval with Joint-Embedding Predictive Architectures","created":"2024-11-29","cited_by_count":0,"area":null},{"id":"2603.28644","title":"Constructing Composite Features for Interpretable Music-Tagging","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2606.30700","title":"BEST-RQ-2: Contextualize-Then-Predict, a Two-Step Approach for Self-Supervised Audio Representations","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.14537","title":"MIDI-RAE-JEPA: Hierarchical Representation Learning and Generation for Symbolic Music","created":"2026-07-16","cited_by_count":0,"area":null}],"next_cursor":null}