{"total":107,"rows":[{"id":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488,"area":null},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448,"area":null},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295,"area":null},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267,"area":null},{"id":"2304.12995","title":"AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head","created":"2023-04-25","cited_by_count":265,"area":null},{"id":"2303.03926","title":"Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling","created":"2023-03-07","cited_by_count":167,"area":null},{"id":"2402.17723","title":"Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners","created":"2024-02-27","cited_by_count":111,"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":"2308.09300","title":"V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models","created":"2023-08-18","cited_by_count":65,"area":null},{"id":"2303.11568","title":"Large AI Models in Health Informatics: Applications, Challenges, and the Future","created":"2023-03-21","cited_by_count":61,"area":null},{"id":"2305.15719","title":"Efficient Neural Music Generation","created":"2023-05-25","cited_by_count":50,"area":null},{"id":"2401.04577","title":"Masked Audio Generation using a Single Non-Autoregressive Transformer","created":"2024-01-09","cited_by_count":50,"area":null},{"id":"2407.05551","title":"Read, Watch and Scream! Sound Generation from Text and Video","created":"2024-07-08","cited_by_count":48,"area":null},{"id":"2308.05037","title":"Separate Anything You Describe","created":"2023-08-09","cited_by_count":43,"area":null},{"id":"2406.04321","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling","created":"2024-06-06","cited_by_count":40,"area":null},{"id":"2303.14676","title":"PDPP: Projected Diffusion for Procedure Planning in Instructional Videos","created":"2023-03-26","cited_by_count":36,"area":null},{"id":"2308.16212","title":"RetroBridge: Modeling Retrosynthesis with Markov Bridges","created":"2023-08-30","cited_by_count":36,"area":null},{"id":"2404.14381","title":"TAVGBench: Benchmarking Text to Audible-Video Generation","created":"2024-04-22","cited_by_count":34,"area":null},{"id":"2210.14661","title":"Full-band General Audio Synthesis with Score-based Diffusion","created":"2022-10-26","cited_by_count":32,"area":null},{"id":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28,"area":null},{"id":"2310.17202","title":"miditok: A Python package for MIDI file tokenization","created":"2023-10-26","cited_by_count":27,"area":null},{"id":"2401.00365","title":"HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes","created":"2023-12-31","cited_by_count":27,"area":null},{"id":"2308.14177","title":"AI-Generated Content (AIGC) for Various Data Modalities: A Survey","created":"2023-08-27","cited_by_count":25,"area":null},{"id":"2309.13664","title":"VoiceLDM: Text-to-Speech with Environmental Context","created":"2023-09-24","cited_by_count":23,"area":null},{"id":"2406.09272","title":"Action2Sound: Ambient-Aware Generation of Action Sounds from Egocentric Videos","created":"2024-06-13","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":"2404.08677","title":"PMG : Personalized Multimodal Generation with Large Language Models","created":"2024-04-07","cited_by_count":19,"area":null},{"id":"2303.11329","title":"Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation","created":"2023-03-20","cited_by_count":18,"area":null},{"id":"2305.06594","title":"V2Meow: Meowing to the Visual Beat via Video-to-Music Generation","created":"2023-05-11","cited_by_count":18,"area":null},{"id":"2305.18375","title":"Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling","created":"2023-05-28","cited_by_count":18,"area":null},{"id":"2401.06395","title":"ModaVerse: Efficiently Transforming Modalities with LLMs","created":"2024-01-12","cited_by_count":18,"area":null},{"id":"2305.01319","title":"Long-Term Rhythmic Video Soundtracker","created":"2023-05-02","cited_by_count":17,"area":null},{"id":"2305.15873","title":"Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)","created":"2023-05-25","cited_by_count":17,"area":null},{"id":"2409.11369","title":"Learning Spatially-Aware Language and Audio Embeddings","created":"2024-09-17","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":"2409.07450","title":"VMAS: Video-to-Music Generation via Semantic Alignment in Web Music Videos","created":"2024-09-11","cited_by_count":15,"area":null},{"id":"2409.13037","title":"DNI: Dilutional Noise Initialization for Diffusion Video Editing","created":"2024-09-19","cited_by_count":12,"area":null},{"id":"2502.06604","title":"Do we really have to filter out random noise in pre-training data for language models?","created":"2025-02-10","cited_by_count":11,"area":null},{"id":"2303.03857","title":"Leveraging Pre-trained AudioLDM for Sound Generation: A Benchmark Study","created":"2023-03-07","cited_by_count":10,"area":null},{"id":"2406.06612","title":"SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound","created":"2024-06-06","cited_by_count":10,"area":null},{"id":"2503.06984","title":"Synchronized Video-to-Audio Generation via Mel Quantization-Continuum Decomposition","created":"2025-03-10","cited_by_count":10,"area":null},{"id":"2408.04224","title":"Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text Guidance","created":"2024-08-08","cited_by_count":9,"area":null},{"id":"2510.11052","title":"Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States","created":"2025-10-13","cited_by_count":9,"area":null},{"id":"2301.08846","title":"Regeneration Learning: A Learning Paradigm for Data Generation","created":"2023-01-21","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":"2503.23331","title":"HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimation","created":"2025-03-30","cited_by_count":8,"area":null},{"id":"2601.14728","title":"AQAScore: Evaluating Semantic Alignment in Text-to-Audio Generation via Audio Question Answering","created":"2026-01-21","cited_by_count":8,"area":null},{"id":"2405.04181","title":"Detecting music deepfakes is easy but actually hard","created":"2024-05-07","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":"2503.12131","title":"DiffGAP: A Lightweight Diffusion Module in Contrastive Space for Bridging Cross-Model Gap","created":"2025-03-15","cited_by_count":7,"area":null},{"id":"2407.11954","title":"Gated Temporal Diffusion for Stochastic Long-Term Dense Anticipation","created":"2024-07-16","cited_by_count":6,"area":null},{"id":"2410.17918","title":"Addressing Asynchronicity in Clinical Multimodal Fusion via Individualized Chest X-ray Generation","created":"2024-10-23","cited_by_count":6,"area":null},{"id":"2402.16021","title":"TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages","created":"2024-02-25","cited_by_count":5,"area":null},{"id":"2406.00146","title":"A Survey of Deep Learning Audio Generation Methods","created":"2024-05-31","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":"2509.23727","title":"AudioMoG: Guiding Audio Generation with Mixture-of-Guidance","created":"2025-09-28","cited_by_count":5,"area":null},{"id":"2307.04292","title":"A Demand-Driven Perspective on Generative Audio AI","created":"2023-07-10","cited_by_count":4,"area":null},{"id":"2406.02315","title":"An Independence-promoting Loss for Music Generation with Language Models","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2410.14971","title":"BrainECHO: Semantic Brain Signal Decoding through Vector-Quantized Spectrogram Reconstruction for Whisper-Enhanced Text Generation","created":"2024-10-19","cited_by_count":4,"area":null},{"id":"2411.00929","title":"Text2Freq: Learning Series Patterns from Text via Frequency Domain","created":"2024-11-01","cited_by_count":4,"area":null},{"id":"2504.00837","title":"A Survey on Music Generation from Single-Modal, Cross-Modal, and Multi-Modal Perspectives","created":"2025-04-01","cited_by_count":4,"area":null},{"id":"2504.07594","title":"Extending Visual Dynamics for Video-to-Music Generation","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2510.21581","title":"Foley Control: Aligning a Frozen Latent Text-to-Audio Model to Video","created":"2025-10-24","cited_by_count":4,"area":null},{"id":"2311.00897","title":"On The Open Prompt Challenge In Conditional Audio Generation","created":"2023-11-01","cited_by_count":3,"area":null},{"id":"2405.14222","title":"Rate-Adaptive Quantization: A Multi-Rate Codebook Adaptation for Vector Quantization-based Generative Models","created":"2024-05-23","cited_by_count":3,"area":null},{"id":"2405.16136","title":"C3LLM: Conditional Multimodal Content Generation Using Large Language Models","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2408.09825","title":"TDNetGen: Empowering Complex Network Resilience Prediction with Generative Augmentation of Topology and Dynamics","created":"2024-08-19","cited_by_count":3,"area":null},{"id":"2409.00851","title":"Dissecting Temporal Understanding in Text-to-Audio Retrieval","created":"2024-09-01","cited_by_count":3,"area":null},{"id":"2409.11498","title":"Augment, Drop & Swap: Improving Diversity in LLM Captions for Efficient Music-Text Representation Learning","created":"2024-09-17","cited_by_count":3,"area":null},{"id":"2410.16239","title":"MoRE: Multi-Modal Contrastive Pre-training with Transformers on X-Rays, ECGs, and Diagnostic Report","created":"2024-10-21","cited_by_count":3,"area":null},{"id":"2412.15922","title":"RiTTA: Modeling Event Relations in Text-to-Audio Generation","created":"2024-12-20","cited_by_count":3,"area":null},{"id":"2506.04214","title":"Sounding that Object: Interactive Object-Aware Image to Audio Generation","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2506.18881","title":"Let Your Video Listen to Your Music!","created":"2025-06-23","cited_by_count":3,"area":null},{"id":"2602.12304","title":"OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Model","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2411.13766","title":"Tiny-Align: Bridging Automatic Speech Recognition and Large Language Model on the Edge","created":"2024-11-21","cited_by_count":2,"area":null},{"id":"2509.05256","title":"Recomposer: Event-roll-guided generative audio editing","created":"2025-09-05","cited_by_count":2,"area":null},{"id":"2512.11912","title":"Robustness of Probabilistic Models to Low-Quality Data: A Multi-Perspective Analysis","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2512.17051","title":"SFBD-OMNI: Bridge models for lossy measurement restoration with limited clean samples","created":"2025-12-18","cited_by_count":2,"area":null},{"id":"2603.11042","title":"V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2603.19857","title":"FoleyDirector: Fine-Grained Temporal Steering for Video-to-Audio Generation via Structured Scripts","created":"2026-03-20","cited_by_count":2,"area":null},{"id":"2304.06602","title":"A-CAP: Anticipation Captioning with Commonsense Knowledge","created":"2023-04-13","cited_by_count":1,"area":null},{"id":"2311.00895","title":"In-Context Prompt Editing For Conditional Audio Generation","created":"2023-11-01","cited_by_count":1,"area":null},{"id":"2402.10941","title":"Text2Data: Low-Resource Data Generation with Textual Control","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2403.01071","title":"GraphRCG: Self-Conditioned Graph Generation","created":"2024-03-02","cited_by_count":1,"area":null},{"id":"2409.18542","title":"MIMII-Gen: Generative Modeling Approach for Simulated Evaluation of Anomalous Sound Detection System","created":"2024-09-27","cited_by_count":1,"area":null},{"id":"2502.00459","title":"AudioGenX: Explainability on Text-to-Audio Generative Models","created":"2025-02-01","cited_by_count":1,"area":null},{"id":"2502.18300","title":"Bayesian Computation in Deep Learning","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2503.14928","title":"Shushing! Let's Imagine an Authentic Speech from the Silent Video","created":"2025-03-19","cited_by_count":1,"area":null},{"id":"2509.23364","title":"AI-Assisted Music Production: A User Study on Text-to-Music Models","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2604.10542","title":"VidAudio-Bench: Benchmarking V2A and VT2A Generation across Four Audio Categories","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2405.11093","title":"AudioSetMix: Enhancing Audio-Language Datasets with LLM-Assisted Augmentations","created":"2024-05-17","cited_by_count":0,"area":null},{"id":"2406.10591","title":"MINT: a Multi-modal Image and Narrative Text Dubbing Dataset for Foley Audio Content Planning and Generation","created":"2024-06-15","cited_by_count":0,"area":null},{"id":"2407.14212","title":"Braille-to-Speech Generator: Audio Generation Based on Joint Fine-Tuning of CLIP and Fastspeech2","created":"2024-07-19","cited_by_count":0,"area":null},{"id":"2409.09381","title":"Text Prompt is Not Enough: Sound Event Enhanced Prompt Adapter for Target Style Audio Generation","created":"2024-09-14","cited_by_count":0,"area":null},{"id":"2505.05381","title":"Towards High Resolution Probabilistic Coastal Inundation Forecasting from Sparse Observations","created":"2025-05-08","cited_by_count":0,"area":null},{"id":"2505.10827","title":"NeuSEditor: From Multi-View Images to Text-Guided Neural Surface Edits","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2505.13777","title":"Sat2Sound: A Unified Framework for Zero-Shot Soundscape Mapping","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2506.16310","title":"Optimizing Multilingual Text-To-Speech with Accents & Emotions","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2507.11096","title":"EditGen: Harnessing Cross-Attention Control for Instruction-Based Auto-Regressive Audio Editing","created":"2025-07-15","cited_by_count":0,"area":null}],"next_cursor":"100"}