{"total":20,"rows":[{"id":"2506.15220","title":"video-SALMONN 2: Caption-Enhanced Audio-Visual Large Language Models","created":"2025-06-18","cited_by_count":47,"area":null},{"id":"2409.11369","title":"Learning Spatially-Aware Language and Audio Embeddings","created":"2024-09-17","cited_by_count":17,"area":null},{"id":"2410.02381","title":"MetaMetrics: Calibrating Metrics For Generation Tasks Using Human Preferences","created":"2024-10-03","cited_by_count":15,"area":null},{"id":"2409.16644","title":"Enabling Auditory Large Language Models for Automatic Speech Quality Evaluation","created":"2024-09-25","cited_by_count":13,"area":null},{"id":"2507.11949","title":"MOSPA: Human Motion Generation Driven by Spatial Audio","created":"2025-07-16","cited_by_count":12,"area":null},{"id":"2601.02954","title":"The World is Not Mono: Enabling Spatial Understanding in Large Audio-Language Models","created":"2026-01-06","cited_by_count":6,"area":null},{"id":"2510.05542","title":"Sci-Phi: A Large Language Model Spatial Audio Descriptor","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2504.08907","title":"Spatial Audio Processing with Large Language Model on Wearable Devices","created":"2025-04-11","cited_by_count":4,"area":null},{"id":"2506.14973","title":"Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2511.13273","title":"AudioMotionBench: Evaluating Auditory Motion Perception in Audio LLMs","created":"2025-11-17","cited_by_count":2,"area":null},{"id":"2609.23407","title":"OmniEcho: Audio-Visual Spatial Understanding for Omni-Modal Embodied Agents","created":"2026-09-20","cited_by_count":2,"area":null},{"id":"2608.02397","title":"Can Foundation Models Hear What Made That Sound? A Tiered Benchmark of Audio-Language Models and Traditional Classifiers for Closed-Set Sound Source Identification","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2606.14820","title":"Spectro-Temporal Interference Confounds Phase Encoding in Spatial Audio Foundation Models","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.15265","title":"SceneBind: Binding What and Where Across Vision, Audio and Language","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2609.23152","title":"Bearings: Self-Supervised Soundfield Embeddings from First-Order Ambisonics","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.29448","title":"YODAS v3: Over 1 Million Hours of High-Bandwidth, Stereophonic, Multilingual Speech","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.34347","title":"SAIL: Spatial Audio Intelligence with Large Language Models via Disentangled Acoustic-Spatial Encoding and Dual-Stream Q-Former","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38748","title":"Hear the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio Generation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01388","title":"Supervising Sound Localization by In-the-wild Egomotion","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.05610","title":"SEA-LM: Egocentric Spatial Audio Understanding for Wearable Microphone Arrays","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}