{"total":46,"rows":[{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771,"area":null},{"id":"2311.07919","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","created":"2023-11-14","cited_by_count":608,"area":null},{"id":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560,"area":null},{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222,"area":null},{"id":"2507.16632","title":"Step-Audio 2 Technical Report","created":"2025-07-22","cited_by_count":105,"area":null},{"id":"2603.27538","title":"LongCat-Next: Lexicalizing Modalities as Discrete Tokens","created":"2026-03-29","cited_by_count":36,"area":null},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2409.11884","title":"Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advances","created":"2024-09-18","cited_by_count":26,"area":null},{"id":"2505.11217","title":"Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization","created":"2025-05-16","cited_by_count":18,"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":"2508.04195","title":"NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations","created":"2025-08-06","cited_by_count":15,"area":null},{"id":"2501.13306","title":"OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia","created":"2025-01-23","cited_by_count":13,"area":null},{"id":"2505.14518","title":"Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples","created":"2025-05-20","cited_by_count":11,"area":null},{"id":"2210.15283","title":"On Out-of-Distribution Detection for Audio with Deep Nearest Neighbors","created":"2022-10-27","cited_by_count":9,"area":null},{"id":"2502.12900","title":"Soundwave: Less is More for Speech-Text Alignment in LLMs","created":"2025-02-18","cited_by_count":7,"area":null},{"id":"2505.22765","title":"StressTest: Can YOUR Speech LM Handle the Stress?","created":"2025-05-28","cited_by_count":7,"area":null},{"id":"2506.00385","title":"MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation","created":"2025-05-31","cited_by_count":7,"area":null},{"id":"2601.19956","title":"VoxPrivacy: A Benchmark for Evaluating Interactional Privacy of Speech Language Models","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2509.14946","title":"SynParaSpeech: Automated Synthesis of Paralinguistic Datasets for Speech Generation and Understanding","created":"2025-09-18","cited_by_count":6,"area":null},{"id":"2601.01373","title":"UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models","created":"2026-01-04","cited_by_count":6,"area":null},{"id":"2601.12248","title":"AQUA-Bench: Beyond Finding Answers to Knowing When There Are None in Audio Question Answering","created":"2026-01-18","cited_by_count":6,"area":null},{"id":"2504.14076","title":"Transformation of audio embeddings into interpretable, concept-based representations","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2401.14625","title":"Toward Practical Automatic Speech Recognition and Post-Processing: a Call for Explainable Error Benchmark Guideline","created":"2024-01-26","cited_by_count":4,"area":null},{"id":"2506.10423","title":"PAL: Probing Audio Encoders via LLMs -- Audio Information Transfer into LLMs","created":"2025-06-12","cited_by_count":3,"area":null},{"id":"2607.18934","title":"Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing","created":"2026-07-21","cited_by_count":3,"area":null},{"id":"2501.00398","title":"TSPE: Task-Specific Prompt Ensemble for Improved Zero-Shot Audio Classification","created":"2024-12-31","cited_by_count":2,"area":null},{"id":"2504.19327","title":"DeepInsert: Early Layer Bypass for Efficient and Performant Multimodal Understanding","created":"2025-04-27","cited_by_count":2,"area":null},{"id":"2507.18061","title":"TELEVAL: A Benchmark Designed for Spoken Language Models in Chinese Interactive Scenarios","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2605.13672","title":"SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2409.07390","title":"D-CAPTCHA++: A Study of Resilience of Deepfake CAPTCHA under Transferable Imperceptible Adversarial Attack","created":"2024-09-11","cited_by_count":1,"area":null},{"id":"2412.17306","title":"Multiple Consistency-guided Test-Time Adaptation for Contrastive Audio-Language Models with Unlabeled Audio","created":"2024-12-23","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":"2510.19368","title":"AMAuT: A Flexible and Efficient Multiview Audio Transformer Framework Trained from Scratch","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2601.05011","title":"Leveraging Prediction Entropy for Automatic Prompt Weighting in Zero-Shot Audio-Language Classification","created":"2026-01-08","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":"2605.18904","title":"Dynamic Model Merging Made Slim","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2606.01016","title":"PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2207.05784","title":"Distilled Non-Semantic Speech Embeddings with Binary Neural Networks for Low-Resource Devices","created":"2022-07-12","cited_by_count":0,"area":null},{"id":"2509.02622","title":"IS${}^3$ : Generic Impulsive--Stationary Sound Separation in Acoustic Scenes using Deep Filtering","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2511.18421","title":"DHAuDS: A Dynamic and Heterogeneous Audio Benchmark for Test-Time Adaptation","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2605.06309","title":"MultiLinguahah : A New Unsupervised Multilingual Acoustic Laughter Segmentation Method","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2608.08989","title":"How Far Do Foundation Models Transfer to Infant Signals? A Cross-Dataset Transfer Audit with a Unified Need Ontology","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.27817","title":"Auditing generative audio calls for known-task audio-llm evaluation","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2608.30456","title":"Self-Supervised Pretext Tasks for Infant Cry Analysis: A Controlled Comparison and a Cautionary Result on Donateacry","created":"2026-08-31","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":"2609.22851","title":"Discrete vs. Continuous: A Comprehensive Study of Unified Audio Understanding in LALMs","created":"2026-09-19","cited_by_count":0,"area":null}],"next_cursor":null}