{"total":15,"rows":[{"id":"2506.18843","title":"USAD: Universal Speech and Audio Representation via Distillation","created":"2025-06-23","cited_by_count":7,"area":null},{"id":"2509.24901","title":"Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2606.25225","title":"MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning","created":"2026-06-23","cited_by_count":2,"area":null},{"id":"2510.15383","title":"DroneAudioset: An Audio Dataset for Drone-based Search and Rescue","created":"2025-10-17","cited_by_count":1,"area":null},{"id":"2605.14231","title":"AudioMosaic: Contrastive Masked Audio Representation Learning","created":"2026-05-14","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":"2608.02397","title":"Can Foundation Models Hear What Made That Sound? A Tiered Benchmark of Audio-Language Models and Traditional Classifiers for Closed-Set Sound Source Identification","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2509.10391","title":"Improving Audio Event Recognition with Consistency Regularization","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2512.03637","title":"AaSP: Aliasing-aware Self-Supervised Pre-Training for Audio Spectrogram Transformers","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2602.16305","title":"BAT: Better Audio Transformer Guided by Convex Gated Probing","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.13749","title":"Sub-Band Spectral Matching with Localized Score Aggregation for Robust Anomalous Sound Detection","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2604.03314","title":"CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream Tasks","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2608.15632","title":"Sparse Prototype Code Underlies Classification and Prediction Across Modalities","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.19863","title":"Listening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learners","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.18041","title":"Correlation-Guided Encoder Selection for Multi-Encoder Large Audio-Language Models","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}