{"total":23,"rows":[{"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":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28,"area":null},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2404.17806","title":"T-CLAP: Temporal-Enhanced Contrastive Language-Audio Pretraining","created":"2024-04-27","cited_by_count":18,"area":null},{"id":"2506.01558","title":"SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes","created":"2025-06-02","cited_by_count":17,"area":null},{"id":"2412.10768","title":"VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation","created":"2024-12-14","cited_by_count":16,"area":null},{"id":"2601.02731","title":"Omni2Sound: Towards Unified Video-Text-to-Audio Generation","created":"2026-01-06","cited_by_count":11,"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":"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":"2511.16757","title":"Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2508.20088","title":"AudioStory: Generating Long-Form Narrative Audio with Large Language Models","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2511.15131","title":"CASTELLA: Long Audio Dataset with Captions and Temporal Boundaries","created":"2025-11-19","cited_by_count":3,"area":null},{"id":"2603.25767","title":"Unlocking Strong Supervision: A Data-Centric Study of General-Purpose Audio Pre-Training Methods","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2510.02322","title":"SpeechCT-CLIP: Distilling Text-Image Knowledge to Speech for Voice-Native Multimodal CT Analysis","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2512.00496","title":"CACARA: Cross-Modal Alignment Leveraging a Text-Centric Approach for Cost-Effective Multimodal and Multilingual Learning","created":"2025-11-29","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":"2601.15118","title":"WavLink: Compact Audio-Text Embeddings with a Global Whisper Token","created":"2026-01-21","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":"2605.29628","title":"COMET: Concept Space Dissection of the Modality Gap in Audio-Text Multimodal Contrastive Embeddings","created":"2026-05-28","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":"2608.24845","title":"LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.02343","title":"SonicCaps: Large-Scale Diverse and Fine-Grained Captioning for Improved Audio-Retrieval","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2610.01861","title":"AVSD-Scenes: A Dataset for Audio-Visual Description of Urban Scenes","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}