{"total":267,"rows":[{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909,"area":"mllm"},{"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":"2308.05734","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","created":"2023-08-10","cited_by_count":344,"area":"diffusion"},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278,"area":"mllm"},{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222,"area":null},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187,"area":"mllm"},{"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":"2408.05211","title":"VITA: Towards Open-Source Interactive Omni Multimodal LLM","created":"2024-08-09","cited_by_count":173,"area":"mllm"},{"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":"2304.13731","title":"Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model","created":"2023-04-24","cited_by_count":145,"area":"lr"},{"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":"2503.03983","title":"Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities","created":"2025-03-06","cited_by_count":133,"area":"lr"},{"id":"2406.16020","title":"AudioBench: A Universal Benchmark for Audio Large Language Models","created":"2024-06-23","cited_by_count":128,"area":null},{"id":"2307.08581","title":"BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs","created":"2023-07-17","cited_by_count":114,"area":"mllm"},{"id":"2405.11273","title":"Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts","created":"2024-05-18","cited_by_count":108,"area":"mllm"},{"id":"2401.06071","title":"GroundingGPT:Language Enhanced Multi-modal Grounding Model","created":"2024-01-11","cited_by_count":101,"area":"mllm"},{"id":"2305.18474","title":"Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation","created":"2023-05-29","cited_by_count":90,"area":"diffusion"},{"id":"2503.23377","title":"JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization","created":"2025-03-30","cited_by_count":88,"area":"diffusion"},{"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":"2312.06720","title":"Audio-Visual LLM for Video Understanding","created":"2023-12-11","cited_by_count":77,"area":"mllm"},{"id":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"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":"2412.21037","title":"TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization","created":"2024-12-30","cited_by_count":68,"area":"diffusion"},{"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":"2401.01044","title":"Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation","created":"2024-01-02","cited_by_count":54,"area":"diffusion"},{"id":"2403.04640","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2024-03-07","cited_by_count":53,"area":"mllm"},{"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":"2507.02768","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","created":"2025-07-03","cited_by_count":50,"area":"synth"},{"id":"2405.19335","title":"X-VILA: Cross-Modality Alignment for Large Language Model","created":"2024-05-29","cited_by_count":46,"area":"alignment"},{"id":"2412.01169","title":"OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows","created":"2024-12-02","cited_by_count":46,"area":"diffusion"},{"id":"2508.16930","title":"HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation","created":"2025-08-23","cited_by_count":46,"area":"diffusion"},{"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":"2502.08826","title":"Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation","created":"2025-02-12","cited_by_count":42,"area":"rag"},{"id":"2503.12769","title":"ViSpeak: Visual Instruction Feedback in Streaming Videos","created":"2025-03-17","cited_by_count":42,"area":"mllm"},{"id":"2506.19774","title":"Kling-Foley: Multimodal Diffusion Transformer for High-Quality Video-to-Audio Generation","created":"2025-06-24","cited_by_count":40,"area":"diffusion"},{"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":"2412.15838","title":"Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback","created":"2024-12-20","cited_by_count":39,"area":"alignment"},{"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":"2409.10819","title":"EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer","created":"2024-09-17","cited_by_count":31,"area":"diffusion"},{"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":"2503.08540","title":"Mellow: a small audio language model for reasoning","created":"2025-03-11","cited_by_count":27,"area":"lr"},{"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":"2410.10676","title":"Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation","created":"2024-10-14","cited_by_count":25,"area":"diffusion"},{"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":"2406.00356","title":"AudioLCM: Text-to-Audio Generation with Latent Consistency Models","created":"2024-06-01","cited_by_count":21,"area":"diffusion"},{"id":"2409.07614","title":"FlowSep: Language-Queried Sound Separation with Rectified Flow Matching","created":"2024-09-11","cited_by_count":21,"area":"diffusion"},{"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":"2511.12609","title":"Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data","created":"2025-11-16","cited_by_count":21,"area":"moe"},{"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":"2308.11940","title":"Audio Generation with Multiple Conditional Diffusion Model","created":"2023-08-23","cited_by_count":18,"area":"diffusion"},{"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":"2411.07076","title":"StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification","created":"2024-11-11","cited_by_count":15,"area":"mllm"},{"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":"2503.01485","title":"FlowDec: A flow-based full-band general audio codec with high perceptual quality","created":"2025-03-03","cited_by_count":15,"area":"diffusion"},{"id":"2503.11411","title":"Empowering Time Series Analysis with Synthetic Data: A Survey and Outlook in the Era of Foundation Models","created":"2025-03-14","cited_by_count":15,"area":"synth"},{"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":"2409.12466","title":"AudioEditor: A Training-Free Diffusion-Based Audio Editing Framework","created":"2024-09-19","cited_by_count":13,"area":"diffusion"},{"id":"2402.12750","title":"Model Composition for Multimodal Large Language Models","created":"2024-02-20","cited_by_count":12,"area":"mllm"},{"id":"2410.20178","title":"LLMs Can Evolve Continually on Modality for X-Modal Reasoning","created":"2024-10-26","cited_by_count":12,"area":"lr"},{"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":"2508.00733","title":"AudioGen-Omni: A Unified Multimodal Diffusion Transformer for Video-Synchronized Audio, Speech, and Song Generation","created":"2025-08-01","cited_by_count":12,"area":"diffusion"},{"id":"2509.21625","title":"Guiding Audio Editing with Audio Language Model","created":"2025-09-25","cited_by_count":12,"area":"diffusion"},{"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":"2410.09472","title":"DRCap: Decoding CLAP Latents with Retrieval-Augmented Generation for Zero-shot Audio Captioning","created":"2024-10-12","cited_by_count":11,"area":"rag"},{"id":"2510.08878","title":"ControlAudio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modeling","created":"2025-10-10","cited_by_count":11,"area":"diffusion"},{"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":"2412.19259","title":"VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesis","created":"2024-12-26","cited_by_count":10,"area":"diffusion"},{"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":"2601.09385","title":"SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing","created":"2026-01-14","cited_by_count":8,"area":"mllm"},{"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}],"next_cursor":"100"}