{"total":97,"rows":[{"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":"2510.01284","title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","created":"2025-09-30","cited_by_count":83,"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":"2411.17698","title":"Video-Guided Foley Sound Generation with Multimodal Controls","created":"2024-11-26","cited_by_count":49,"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":"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":"2406.05534","title":"Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing","created":"2024-06-08","cited_by_count":39,"area":"alignment"},{"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":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28,"area":null},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","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":"2410.10676","title":"Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation","created":"2024-10-14","cited_by_count":25,"area":"diffusion"},{"id":"2506.07520","title":"LeVo: High-Quality Song Generation with Multi-Preference Alignment","created":"2025-06-09","cited_by_count":25,"area":"alignment"},{"id":"2502.15602","title":"KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio Generation","created":"2025-02-21","cited_by_count":24,"area":null},{"id":"2411.01834","title":"Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback","created":"2024-11-04","cited_by_count":23,"area":"alignment"},{"id":"2412.15191","title":"AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation","created":"2024-12-19","cited_by_count":22,"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":"2409.12403","title":"Preference Alignment Improves Language Model-Based TTS","created":"2024-09-19","cited_by_count":21,"area":"alignment"},{"id":"2406.15487","title":"Improving Text-To-Audio Models with Synthetic Captions","created":"2024-06-18","cited_by_count":19,"area":null},{"id":"2410.12266","title":"FlashAudio: Rectified Flows for Fast and High-Fidelity Text-to-Audio Generation","created":"2024-10-16","cited_by_count":19,"area":"diffusion"},{"id":"2412.04782","title":"A Survey of Sustainability in Large Language Models: Applications, Economics, and Challenges","created":"2024-12-06","cited_by_count":18,"area":null},{"id":"2405.12221","title":"Images that Sound: Composing Images and Sounds on a Single Canvas","created":"2024-05-20","cited_by_count":17,"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":"2412.10768","title":"VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation","created":"2024-12-14","cited_by_count":16,"area":null},{"id":"2412.05095","title":"SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization","created":"2024-12-06","cited_by_count":15,"area":"alignment"},{"id":"2503.20782","title":"Zero-Shot Audio-Visual Editing via Cross-Modal Delta Denoising","created":"2025-03-26","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":"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":"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":"2510.23451","title":"Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences","created":"2025-10-27","cited_by_count":11,"area":"alignment"},{"id":"2601.02731","title":"Omni2Sound: Towards Unified Video-Text-to-Audio Generation","created":"2026-01-06","cited_by_count":11,"area":null},{"id":"2507.20880","title":"JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment","created":"2025-07-28","cited_by_count":9,"area":"diffusion"},{"id":"2410.02056","title":"Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data","created":"2024-10-02","cited_by_count":7,"area":"synth"},{"id":"2508.18781","title":"AniME: Adaptive Multi-Agent Planning for Long Animation Generation","created":"2025-08-26","cited_by_count":7,"area":null},{"id":"2410.13754","title":"MixEval-X: Any-to-Any Evaluations from Real-World Data Mixtures","created":"2024-10-17","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":"2505.17613","title":"MMMG: a Comprehensive and Reliable Benchmark for Multitask Multimodal Generation","created":"2025-05-23","cited_by_count":6,"area":null},{"id":"2507.11554","title":"Inversion-DPO: Precise and Efficient Post-Training for Diffusion Models","created":"2025-07-14","cited_by_count":6,"area":"diffusion"},{"id":"2509.24391","title":"UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities","created":"2025-09-29","cited_by_count":6,"area":"diffusion"},{"id":"2605.17991","title":"Stable Audio 3","created":"2026-05-18","cited_by_count":6,"area":"diffusion"},{"id":"2606.30642","title":"LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2502.05130","title":"Latent Swap Joint Diffusion for 2D Long-Form Latent Generation","created":"2025-02-07","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":"2508.16332","title":"Vevo2: A Unified and Controllable Framework for Speech and Singing Voice Generation","created":"2025-08-22","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":"2512.10264","title":"MR-FlowDPO: Multi-Reward Direct Preference Optimization for Flow-Matching Text-to-Music Generation","created":"2025-12-11","cited_by_count":5,"area":"diffusion"},{"id":"2504.15217","title":"DRAGON: Distributional Rewards Optimize Diffusion Generative Models","created":"2025-04-21","cited_by_count":4,"area":"diffusion"},{"id":"2505.17417","title":"Speechless: Speech Instruction Training Without Speech for Low Resource Languages","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2505.23950","title":"InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback","created":"2025-05-29","cited_by_count":4,"area":"alignment"},{"id":"2509.18928","title":"Direct Preference Optimization for Speech Autoregressive Diffusion Models","created":"2025-09-23","cited_by_count":4,"area":"diffusion"},{"id":"2606.17006","title":"TuneJury: An Open Metric for Improving Music Generation Preference Alignment","created":"2026-06-15","cited_by_count":4,"area":"alignment"},{"id":"2409.13894","title":"PTQ4ADM: Post-Training Quantization for Efficient Text Conditional Audio Diffusion Models","created":"2024-09-20","cited_by_count":3,"area":"diffusion"},{"id":"2412.15922","title":"RiTTA: Modeling Event Relations in Text-to-Audio Generation","created":"2024-12-20","cited_by_count":3,"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":"2607.20166","title":"Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning","created":"2026-07-22","cited_by_count":3,"area":"lr"},{"id":"2410.23815","title":"The NPU-HWC System for the ISCSLP 2024 Inspirational and Convincing Audio Generation Challenge","created":"2024-10-31","cited_by_count":2,"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":"2502.18952","title":"DualSpec: Text-to-spatial-audio Generation via Dual-Spectrogram Guided Diffusion Model","created":"2025-02-26","cited_by_count":2,"area":"diffusion"},{"id":"2506.09874","title":"UmbraTTS: Adapting Text-to-Speech to Environmental Contexts with Flow Matching","created":"2025-06-11","cited_by_count":2,"area":"diffusion"},{"id":"2508.21407","title":"DRASP: A Dual-Resolution Attentive Statistics Pooling Framework for Automatic MOS Prediction","created":"2025-08-29","cited_by_count":2,"area":null},{"id":"2509.14934","title":"Mitigating data replication in text-to-audio generative diffusion models through anti-memorization guidance","created":"2025-09-18","cited_by_count":2,"area":"diffusion"},{"id":"2603.19176","title":"Few-shot Acoustic Synthesis with Multimodal Flow Matching","created":"2026-03-19","cited_by_count":2,"area":"diffusion"},{"id":"2605.18749","title":"WavFlow: Audio Generation in Waveform Space","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2407.10328","title":"The Interpretation Gap in Text-to-Music Generation Models","created":"2024-07-14","cited_by_count":1,"area":null},{"id":"2502.18532","title":"CuDIP: Enhancing Theorem Proving in LLMs via Curriculum Learning-based Direct Preference Optimization","created":"2025-02-25","cited_by_count":1,"area":"lr"},{"id":"2505.18453","title":"MPE-TTS: Customized Emotion Zero-Shot Text-To-Speech Using Multi-Modal Prompt","created":"2025-05-24","cited_by_count":1,"area":null},{"id":"2508.13786","title":"DegDiT: Controllable Audio Generation with Dynamic Event Graph Guided Diffusion Transformer","created":"2025-08-19","cited_by_count":1,"area":"diffusion"},{"id":"2512.12769","title":"Adaptive Edge-Cloud Inference for Speech-to-Action Systems Using ASR and Large Language Models","created":"2025-12-14","cited_by_count":1,"area":null},{"id":"2603.07025","title":"Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision","created":"2026-03-07","cited_by_count":1,"area":null},{"id":"2604.04348","title":"OmniSonic: Towards Universal and Holistic Audio Generation from Video and Text","created":"2026-04-06","cited_by_count":1,"area":"moe"},{"id":"2604.05731","title":"FoleyDesigner: Immersive Stereo Foley Generation with Precise Spatio-Temporal Alignment for Film Clips","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2605.30940","title":"Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer","created":"2026-05-29","cited_by_count":1,"area":"diffusion"},{"id":"2606.12555","title":"AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation","created":"2026-06-10","cited_by_count":1,"area":"diffusion"},{"id":"2606.18273","title":"Continuous Audio Thinking for Large Audio Language Models","created":"2026-06-05","cited_by_count":1,"area":"lr"},{"id":"2606.31259","title":"SwiftAudio: Data-Efficient Caption-Only Distillation for One-Step Text-to-Audio Diffusion-based Generation","created":"2026-06-30","cited_by_count":1,"area":"diffusion"},{"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":"2503.22200","title":"Enhance Generation Quality of Flow Matching V2A Model via Multi-Step CoT-Like Guidance and Combined Preference Optimization","created":"2025-03-28","cited_by_count":0,"area":"diffusion"},{"id":"2505.13777","title":"Sat2Sound: A Unified Framework for Zero-Shot Soundscape Mapping","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2507.20666","title":"MIMII-Agent: Leveraging LLMs with Function Calling for Relative Evaluation of Anomalous Sound Detection","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2511.07806","title":"PC-Diffusion: Aligning Diffusion Models with Human Preferences via Preference Classifier","created":"2025-11-11","cited_by_count":0,"area":"diffusion"},{"id":"2603.01565","title":"Investigating Group Relative Policy Optimization for Diffusion Transformer based Text-to-Audio Generation","created":"2026-03-02","cited_by_count":0,"area":"diffusion"},{"id":"2605.04547","title":"Stage-adaptive audio diffusion modeling","created":"2026-05-06","cited_by_count":0,"area":"diffusion"},{"id":"2606.14049","title":"FoleyGenEx: Unified Video-to-Audio Generation with Multi-Modal Control, Temporal Alignment, and Semantic Precision","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.20101","title":"RFM-Editing 2: Text-Guided Audio Editing with Rectified Flow Matching and Coarse-to-Fine Diffusion Transformers","created":"2026-06-18","cited_by_count":0,"area":"diffusion"},{"id":"2606.23064","title":"STAR-VAE: Structured Topology-Aware Regularization for Audio Reconstruction and Generation","created":"2026-06-22","cited_by_count":0,"area":"diffusion"},{"id":"2607.05198","title":"Noisy-Channel Minimum Bayes Risk Decoding","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.09973","title":"A Production-Oriented Framework for Evaluation of SFX Generation","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.11364","title":"BackgroundMellow: A Multi-Modal Cohesive Framework for Narrative-Driven Rich Cinematic Soundscape Generation","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.13408","title":"Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language Models","created":"2026-07-15","cited_by_count":0,"area":"alignment"},{"id":"2608.00463","title":"Scene2Sound: Auditory-Grounded Soundscape Generation for 3D Gaussian Worlds","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.03742","title":"AI-Based Sound Effect Generation: A Narrative Review of Generative Models Across Input Modalities","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.11913","title":"HarmoniDPO: Video-guided Audio Generation via Preference-Optimized Diffusion","created":"2026-08-12","cited_by_count":0,"area":"alignment"},{"id":"2608.12951","title":"VoxAudio: Vocalized Audio Synthesis via Multi-Reward Autoregressive Flow Matching","created":"2026-08-13","cited_by_count":0,"area":"diffusion"},{"id":"2609.28206","title":"UNITE-AUDIO: Joint Learning of Continuous Tokenization and Latent Flow Matching for Text-to-Audio Generation","created":"2026-09-23","cited_by_count":0,"area":"diffusion"},{"id":"2609.29816","title":"AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.38444","title":"Audible World Models: Spatially Aware Sound Generation for 3D Worlds","created":"2026-09-29","cited_by_count":0,"area":"wm"}],"next_cursor":null}