{"total":19,"rows":[{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222,"area":null},{"id":"2209.14275","title":"Audio Retrieval with WavText5K and CLAP Training","created":"2022-09-28","cited_by_count":35,"area":null},{"id":"2602.19163","title":"JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation","created":"2026-02-22","cited_by_count":25,"area":null},{"id":"2506.00343","title":"The iNaturalist Sounds Dataset","created":"2025-05-31","cited_by_count":17,"area":null},{"id":"2510.00050","title":"Object-AVEdit: An Object-level Audio-Visual Editing Model","created":"2025-09-27","cited_by_count":14,"area":null},{"id":"2112.03529","title":"Ground-Truth, Whose Truth? -- Examining the Challenges with Annotating Toxic Text Datasets","created":"2021-12-07","cited_by_count":11,"area":null},{"id":"2211.07737","title":"Describing emotions with acoustic property prompts for speech emotion recognition","created":"2022-11-14","cited_by_count":5,"area":null},{"id":"2507.09834","title":"Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction","created":"2025-07-14","cited_by_count":5,"area":null},{"id":"2510.22795","title":"SAO-Instruct: Free-form Audio Editing using Natural Language Instructions","created":"2025-10-26","cited_by_count":4,"area":null},{"id":"2305.01864","title":"Unsupervised Improvement of Audio-Text Cross-Modal Representations","created":"2023-05-03","cited_by_count":3,"area":null},{"id":"2310.02298","title":"Prompting Audios Using Acoustic Properties For Emotion Representation","created":"2023-10-03","cited_by_count":3,"area":null},{"id":"2401.04935","title":"Learning Audio Concepts from Counterfactual Natural Language","created":"2024-01-10","cited_by_count":3,"area":null},{"id":"2405.17615","title":"Listenable Maps for Zero-Shot Audio Classifiers","created":"2024-05-27","cited_by_count":3,"area":null},{"id":"2509.20072","title":"From Text to Talk: Audio-Language Model Needs Non-Autoregressive Joint Training","created":"2025-09-24","cited_by_count":3,"area":null},{"id":"2408.13068","title":"On Class Separability Pitfalls In Audio-Text Contrastive Zero-Shot Learning","created":"2024-08-23","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":"2405.11093","title":"AudioSetMix: Enhancing Audio-Language Datasets with LLM-Assisted Augmentations","created":"2024-05-17","cited_by_count":0,"area":null},{"id":"2601.21612","title":"Representation-Regularized Convolutional Audio Transformer for Audio Understanding","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2605.19101","title":"Heterogeneity-Aware Dataset Scheduling for Efficient Audio Large Language Model Training","created":"2026-05-18","cited_by_count":0,"area":null}],"next_cursor":null}