{"total":16,"rows":[{"id":"2405.09589","title":"A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models","created":"2024-05-15","cited_by_count":100,"area":null},{"id":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28,"area":null},{"id":"2506.11350","title":"GLAP: General contrastive audio-text pretraining across domains and languages","created":"2025-06-12","cited_by_count":10,"area":null},{"id":"2406.07012","title":"Bridging Language Gaps in Audio-Text Retrieval","created":"2024-06-11","cited_by_count":6,"area":null},{"id":"2410.02271","title":"CoLLAP: Contrastive Long-form Language-Audio Pretraining with Musical Temporal Structure Augmentation","created":"2024-10-03","cited_by_count":4,"area":null},{"id":"2511.16757","title":"Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2607.18666","title":"Fusion Embedding: A Unified Embedding Space for Text, Image, Video, and Audio","created":"2026-07-21","cited_by_count":3,"area":null},{"id":"2406.15897","title":"Fusing Audio and Metadata Embeddings Improves Language-based Audio Retrieval","created":"2024-06-22","cited_by_count":2,"area":null},{"id":"2408.11641","title":"Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval","created":"2024-08-21","cited_by_count":2,"area":null},{"id":"2501.03038","title":"Piano Transcription by Hierarchical Language Modeling with Pretrained Roll-based Encoders","created":"2025-01-06","cited_by_count":1,"area":null},{"id":"2509.04606","title":"Sample-efficient Integration of New Modalities into Large Language Models","created":"2025-09-04","cited_by_count":1,"area":null},{"id":"2603.25767","title":"Unlocking Strong Supervision: A Data-Centric Study of General-Purpose Audio Pre-Training Methods","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2509.09717","title":"Testing chatbots on the creation of encoders for audio conditioned image generation","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2601.12594","title":"SLAP: Scalable Language-Audio Pretraining with Variable-Duration Audio and Multi-Objective Training","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2604.16247","title":"Joint-Centric Dual Contrastive Alignment with Structure-Preserving and Information-Balanced Regularization","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2609.32016","title":"VoiceNet: Fine-Grained Voice Understanding Beyond Emotion at Scale","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}