{"total":19,"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":"2412.19351","title":"ETTA: Elucidating the Design Space of Text-to-Audio Models","created":"2024-12-26","cited_by_count":17,"area":null},{"id":"2512.19687","title":"Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning","created":"2025-12-22","cited_by_count":13,"area":null},{"id":"2501.09291","title":"LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport","created":"2025-01-16","cited_by_count":7,"area":null},{"id":"2507.23511","title":"MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2405.16136","title":"C3LLM: Conditional Multimodal Content Generation Using Large Language Models","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2409.01201","title":"EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance","created":"2024-09-02","cited_by_count":3,"area":null},{"id":"2506.00800","title":"CLAP-ART: Automated Audio Captioning with Semantic-rich Audio Representation Tokenizer","created":"2025-06-01","cited_by_count":3,"area":null},{"id":"2409.01160","title":"Expanding on EnCLAP with Auxiliary Retrieval Model for Automated Audio Captioning","created":"2024-09-02","cited_by_count":1,"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":"2502.05435","title":"Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning","created":"2025-02-08","cited_by_count":1,"area":null},{"id":"2510.14249","title":"Do Joint Language-Audio Embeddings Encode Perceptual Timbre Semantics?","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2601.04658","title":"LAMB: LLM-based Audio Captioning with Modality Gap Bridging via Cauchy-Schwarz Divergence","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2508.08924","title":"EGGCodec: A Robust Neural Encodec Framework for EGG Reconstruction and F0 Extraction","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2512.10170","title":"Semantic-Aware Confidence Calibration for Automated Audio Captioning","created":"2025-12-11","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":"2604.23323","title":"Robust Audio-Text Retrieval via Cross-Modal Attention and Hybrid Loss","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2607.04619","title":"CARD: Cross-component Audio Representation Distillation for Encoder-Free Audio Captioning","created":"2026-07-06","cited_by_count":0,"area":null}],"next_cursor":null}