{"total":28,"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":"2501.00365","title":"Low-Rank Adaptation for Foundation Models: A Comprehensive Review","created":"2024-12-31","cited_by_count":37,"area":null},{"id":"2507.02915","title":"Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning","created":"2025-06-25","cited_by_count":17,"area":null},{"id":"2406.13275","title":"Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding","created":"2024-06-19","cited_by_count":14,"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":"2501.09291","title":"LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport","created":"2025-01-16","cited_by_count":7,"area":null},{"id":"2406.07012","title":"Bridging Language Gaps in Audio-Text Retrieval","created":"2024-06-11","cited_by_count":6,"area":null},{"id":"2502.14627","title":"ATRI: Mitigating Multilingual Audio Text Retrieval Inconsistencies by Reducing Data Distribution Errors","created":"2025-02-20","cited_by_count":6,"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":"2310.15648","title":"Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2409.07016","title":"Improving Anomalous Sound Detection via Low-Rank Adaptation Fine-Tuning of Pre-Trained Audio Models","created":"2024-09-11","cited_by_count":3,"area":null},{"id":"2507.16696","title":"FISHER: A Foundation Model for Multi-Modal Industrial Signal Comprehensive Representation","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2506.10312","title":"AC/DC: LLM-based Audio Comprehension via Dialogue Continuation","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2509.14427","title":"Hashing-Baseline: Rethinking Hashing in the Age of Pretrained Models","created":"2025-09-17","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":"2503.21826","title":"Hierarchical Label Propagation: A Model-Size-Dependent Performance Booster for AudioSet Tagging","created":"2025-03-26","cited_by_count":0,"area":null},{"id":"2506.02088","title":"Enhancing Speech Emotion Recognition with Graph-Based Multimodal Fusion and Prosodic Features for the Speech Emotion Recognition in Naturalistic Conditions Challenge at Interspeech 2025","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2508.14689","title":"ECHO: Frequency-aware Hierarchical Encoding for Variable-length Signals","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2512.19703","title":"ASK: Adaptive Self-improving Knowledge Framework for Audio Text Retrieval","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":"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":"2603.27667","title":"EvA: An Evidence-First Audio Understanding Paradigm for LALMs","created":"2026-03-29","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},{"id":"2608.15632","title":"Sparse Prototype Code Underlies Classification and Prediction Across Modalities","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.19174","title":"Finetuning Strategies for Querying Sounds by Vocal Imitation","created":"2026-08-19","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},{"id":"2609.26028","title":"REVE: Efficient Hallucination Correction for Large Audio-Language Models via Reused Encoder States","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.28344","title":"Mizar: A 159M-Parameter Audio-Language Model for Audio Understanding","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}