{"total":184,"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":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506,"area":null},{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222,"area":null},{"id":"2402.01831","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","created":"2024-02-02","cited_by_count":186,"area":null},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169,"area":null},{"id":"2412.15322","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","created":"2024-12-19","cited_by_count":134,"area":null},{"id":"2406.16020","title":"AudioBench: A Universal Benchmark for Audio Large Language Models","created":"2024-06-23","cited_by_count":128,"area":null},{"id":"2502.04328","title":"Ola: Pushing the Frontiers of Omni-Modal Language Model","created":"2025-02-06","cited_by_count":83,"area":null},{"id":"2510.01284","title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","created":"2025-09-30","cited_by_count":83,"area":null},{"id":"2310.04673","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","created":"2023-10-07","cited_by_count":78,"area":null},{"id":"2408.17175","title":"Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model","created":"2024-08-30","cited_by_count":72,"area":null},{"id":"2305.16103","title":"ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst","created":"2023-05-25","cited_by_count":66,"area":null},{"id":"2501.15111","title":"HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding","created":"2025-01-25","cited_by_count":60,"area":null},{"id":"2410.18325","title":"AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models","created":"2024-10-23","cited_by_count":56,"area":null},{"id":"2411.19772","title":"LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos","created":"2024-11-29","cited_by_count":51,"area":null},{"id":"2405.00233","title":"SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound","created":"2024-04-30","cited_by_count":45,"area":null},{"id":"2308.05037","title":"Separate Anything You Describe","created":"2023-08-09","cited_by_count":43,"area":null},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43,"area":null},{"id":"2309.07314","title":"AudioSR: Versatile Audio Super-resolution at Scale","created":"2023-09-13","cited_by_count":39,"area":null},{"id":"2407.11895","title":"OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces","created":"2024-07-16","cited_by_count":39,"area":null},{"id":"2404.14381","title":"TAVGBench: Benchmarking Text to Audible-Video Generation","created":"2024-04-22","cited_by_count":34,"area":null},{"id":"2309.11500","title":"Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning","created":"2023-09-20","cited_by_count":33,"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":"2401.17690","title":"EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning","created":"2024-01-31","cited_by_count":28,"area":null},{"id":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28,"area":null},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2503.10522","title":"AudioX: A Unified Framework for Anything-to-Audio Generation","created":"2025-03-13","cited_by_count":27,"area":null},{"id":"2407.07464","title":"Video-to-Audio Generation with Hidden Alignment","created":"2024-07-10","cited_by_count":26,"area":null},{"id":"2602.19163","title":"JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation","created":"2026-02-22","cited_by_count":25,"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":"2308.04978","title":"Transferable Models for Bioacoustics with Human Language Supervision","created":"2023-08-09","cited_by_count":21,"area":null},{"id":"2507.08557","title":"FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation","created":"2025-07-11","cited_by_count":21,"area":null},{"id":"2408.13608","title":"SpeechCraft: A Fine-grained Expressive Speech Dataset with Natural Language Description","created":"2024-08-24","cited_by_count":20,"area":null},{"id":"2406.15487","title":"Improving Text-To-Audio Models with Synthetic Captions","created":"2024-06-18","cited_by_count":19,"area":null},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2412.19351","title":"ETTA: Elucidating the Design Space of Text-to-Audio Models","created":"2024-12-26","cited_by_count":17,"area":null},{"id":"2506.00343","title":"The iNaturalist Sounds Dataset","created":"2025-05-31","cited_by_count":17,"area":null},{"id":"2408.11915","title":"Video-Foley: Two-Stage Video-To-Sound Generation via Temporal Event Condition For Foley Sound","created":"2024-08-21","cited_by_count":16,"area":null},{"id":"2502.07461","title":"JamendoMaxCaps: A Large Scale Music-caption Dataset with Imputed Metadata","created":"2025-02-11","cited_by_count":15,"area":null},{"id":"2404.16969","title":"COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations","created":"2024-04-25","cited_by_count":14,"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":"2508.06098","title":"MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows","created":"2025-08-08","cited_by_count":14,"area":null},{"id":"2501.14755","title":"Data-Juicer 2.0: Cloud-Scale Adaptive Data Processing for and with Foundation Models","created":"2024-12-23","cited_by_count":12,"area":null},{"id":"2604.10708","title":"Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing","created":"2026-04-12","cited_by_count":12,"area":null},{"id":"2311.08396","title":"Zero-shot audio captioning with audio-language model guidance and audio context keywords","created":"2023-11-14","cited_by_count":11,"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":"2606.01802","title":"MOSS-Audio Technical Report","created":"2026-06-01","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":"2508.09085","title":"Dynamic Uncertainty-aware Multimodal Fusion for Outdoor Health Monitoring","created":"2025-08-12","cited_by_count":10,"area":null},{"id":"2305.09690","title":"A Whisper transformer for audio captioning trained with synthetic captions and transfer learning","created":"2023-05-15","cited_by_count":9,"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":"2309.12242","title":"Weakly-supervised Automated Audio Captioning via text only training","created":"2023-09-21","cited_by_count":8,"area":null},{"id":"2409.14340","title":"Self-Supervised Audio-Visual Soundscape Stylization","created":"2024-09-22","cited_by_count":8,"area":null},{"id":"2404.07616","title":"Audio Dialogues: Dialogues dataset for audio and music understanding","created":"2024-04-11","cited_by_count":7,"area":null},{"id":"2409.06135","title":"Draw an Audio: Leveraging Multi-Instruction for Video-to-Audio Synthesis","created":"2024-09-10","cited_by_count":7,"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":"2512.07209","title":"Coherent Audio-Visual Editing via Conditional Audio Generation Following Video Edits","created":"2025-12-08","cited_by_count":7,"area":null},{"id":"2605.30073","title":"Native Audio-Visual Alignment for Generation","created":"2026-05-28","cited_by_count":7,"area":null},{"id":"2308.04258","title":"Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets","created":"2023-08-08","cited_by_count":6,"area":null},{"id":"2406.07012","title":"Bridging Language Gaps in Audio-Text Retrieval","created":"2024-06-11","cited_by_count":6,"area":null},{"id":"2410.17589","title":"Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio Generation","created":"2024-10-23","cited_by_count":6,"area":null},{"id":"2506.01111","title":"FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion","created":"2025-06-01","cited_by_count":6,"area":null},{"id":"2507.02864","title":"The Sound of Simulation: Learning Multimodal Sim-to-Real Robot Policies with Generative Audio","created":"2025-07-03","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":"2512.24731","title":"EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation","created":"2025-12-31","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":"2602.07960","title":"D-ORCA: Dialogue-Centric Optimization for Robust Audio-Visual Captioning","created":"2026-02-08","cited_by_count":6,"area":null},{"id":"2605.08729","title":"Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation","created":"2026-05-09","cited_by_count":6,"area":null},{"id":"2309.03340","title":"Parameter Efficient Audio Captioning With Faithful Guidance Using Audio-text Shared Latent Representation","created":"2023-09-06","cited_by_count":5,"area":null},{"id":"2406.09412","title":"Explore the Limits of Omni-modal Pretraining at Scale","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2503.22265","title":"DeepAudio-V1:Towards Multi-Modal Multi-Stage End-to-End Video to Speech and Audio Generation","created":"2025-03-28","cited_by_count":5,"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":"2507.09834","title":"Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction","created":"2025-07-14","cited_by_count":5,"area":null},{"id":"2510.02110","title":"SoundReactor: Frame-level Online Video-to-Audio Generation","created":"2025-10-02","cited_by_count":5,"area":null},{"id":"2409.15672","title":"Language-based Audio Moment Retrieval","created":"2024-09-24","cited_by_count":4,"area":null},{"id":"2505.16774","title":"IFEval-Audio: Benchmarking Instruction-Following Capability in Audio-based Large Language Models","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2505.17114","title":"RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2508.03955","title":"Scaling Up Audio-Synchronized Visual Animation: An Efficient Training Paradigm","created":"2025-08-05","cited_by_count":4,"area":null},{"id":"2510.11129","title":"video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLM","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2510.22795","title":"SAO-Instruct: Free-form Audio Editing using Natural Language Instructions","created":"2025-10-26","cited_by_count":4,"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":"2603.15597","title":"AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2604.01929","title":"Woosh: A Sound Effects Foundation Model","created":"2026-04-02","cited_by_count":4,"area":null},{"id":"2308.15090","title":"Killing two birds with one stone: Can an audio captioning system also be used for audio-text retrieval?","created":"2023-08-29","cited_by_count":3,"area":null},{"id":"2401.04935","title":"Learning Audio Concepts from Counterfactual Natural Language","created":"2024-01-10","cited_by_count":3,"area":null},{"id":"2409.01201","title":"EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance","created":"2024-09-02","cited_by_count":3,"area":null},{"id":"2409.13676","title":"A sound description: Exploring prompt templates and class descriptions to enhance zero-shot audio classification","created":"2024-09-19","cited_by_count":3,"area":null},{"id":"2506.00800","title":"CLAP-ART: Automated Audio Captioning with Semantic-rich Audio Representation Tokenizer","created":"2025-06-01","cited_by_count":3,"area":null},{"id":"2508.15418","title":"LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2510.09065","title":"MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation","created":"2025-10-10","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":"2601.23161","title":"DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2603.02098","title":"Efficient and High-Fidelity Omni Modality Retrieval","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2607.18666","title":"Fusion Embedding: A Unified Embedding Space for Text, Image, Video, and Audio","created":"2026-07-21","cited_by_count":3,"area":null},{"id":"2406.15897","title":"Fusing Audio and Metadata Embeddings Improves Language-based Audio Retrieval","created":"2024-06-22","cited_by_count":2,"area":null},{"id":"2408.11641","title":"Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval","created":"2024-08-21","cited_by_count":2,"area":null},{"id":"2409.06635","title":"MoWE-Audio: Multitask AudioLLMs with Mixture of Weak Encoders","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2409.08199","title":"AudioBERT: Audio Knowledge Augmented Language Model","created":"2024-09-12","cited_by_count":2,"area":null},{"id":"2502.12623","title":"DeepResonance: Enhancing Multimodal Music Understanding via Music-centric Multi-way Instruction Tuning","created":"2025-02-18","cited_by_count":2,"area":null}],"next_cursor":"100"}