{"total":13,"rows":[{"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":"2505.07609","title":"TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining","created":"2025-05-12","cited_by_count":9,"area":null},{"id":"2601.06896","title":"TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal Grounding","created":"2026-01-11","cited_by_count":5,"area":null},{"id":"2606.07229","title":"MMAE: A Massive Multitask Audio Editing Benchmark","created":"2026-06-05","cited_by_count":5,"area":null},{"id":"2506.09707","title":"Fine-Tuning Large Audio-Language Models with LoRA for Precise Temporal Localization of Prolonged Exposure Therapy Elements","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2602.14612","title":"Event-Grounded Question Answering over Long Audio via Structured Retrieval","created":"2026-02-16","cited_by_count":2,"area":null},{"id":"2508.07829","title":"Auditory Intelligence: Understanding the World Through Sound","created":"2025-08-11","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":"2512.19703","title":"ASK: Adaptive Self-improving Knowledge Framework for Audio Text Retrieval","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2605.18916","title":"CounterFlow: A Two-Phase Inference-Time Sampling for Counterfactual Video Foley Generation","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.06615","title":"FIGMA: Towards FIne-Grained Music retrievAl","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2607.10023","title":"Local Multimodal Music Alignment from Global Supervision","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2610.13112","title":"Does Location Matter? A Black-Box Causal Audit Reveals Model-Dependent Audio Grounding in LALM Hallucination","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}