{"total":197,"rows":[{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568,"area":null},{"id":"2410.19168","title":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark","created":"2024-10-24","cited_by_count":288,"area":"lr"},{"id":"2509.06155","title":"UniVerse-1: Unified Audio-Video Generation via Stitching of Experts","created":"2025-09-07","cited_by_count":61,"area":null},{"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":"2503.06955","title":"Motion Anything: Any to Motion Generation","created":"2025-03-10","cited_by_count":42,"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":"2410.18881","title":"Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferences","created":"2024-10-24","cited_by_count":31,"area":"diffusion"},{"id":"2603.06507","title":"Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis","created":"2026-03-06","cited_by_count":31,"area":"diffusion"},{"id":"2502.13128","title":"SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation","created":"2025-02-18","cited_by_count":29,"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":"2410.19310","title":"Flow Generator Matching","created":"2024-10-25","cited_by_count":26,"area":"diffusion"},{"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":"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":"2506.07634","title":"SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement","created":"2025-06-09","cited_by_count":23,"area":"diffusion"},{"id":"2411.10510","title":"SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers","created":"2024-11-15","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":"2409.00587","title":"FLUX that Plays Music","created":"2024-09-01","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":"2510.22950","title":"DiffRhythm 2: Efficient and High Fidelity Song Generation via Block Flow Matching","created":"2025-10-27","cited_by_count":15,"area":"diffusion"},{"id":"2505.08175","title":"Fast Text-to-Audio Generation with Adversarial Post-Training","created":"2025-05-13","cited_by_count":14,"area":null},{"id":"2509.17609","title":"Audio Super-Resolution with Latent Bridge Models","created":"2025-09-22","cited_by_count":14,"area":null},{"id":"2510.00050","title":"Object-AVEdit: An Object-level Audio-Visual Editing Model","created":"2025-09-27","cited_by_count":14,"area":null},{"id":"2409.15157","title":"LoVA: Long-form Video-to-Audio Generation","created":"2024-09-23","cited_by_count":13,"area":"diffusion"},{"id":"2410.05151","title":"Editing Music with Melody and Text: Using ControlNet for Diffusion Transformer","created":"2024-10-07","cited_by_count":13,"area":"diffusion"},{"id":"2412.10783","title":"Video Diffusion Transformers are In-Context Learners","created":"2024-12-14","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":"2410.23005","title":"Improving Musical Accompaniment Co-creation via Diffusion Transformers","created":"2024-10-30","cited_by_count":11,"area":"diffusion"},{"id":"2510.03117","title":"Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction","created":"2025-10-03","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":"2506.05104","title":"Survey on the Evaluation of Generative Models in Music","created":"2025-06-05","cited_by_count":10,"area":null},{"id":"2508.04651","title":"Live Music Models","created":"2025-08-06","cited_by_count":10,"area":null},{"id":"2510.12000","title":"UALM: Unified Audio Language Model for Understanding, Generation and Reasoning","created":"2025-10-13","cited_by_count":10,"area":"lr"},{"id":"2601.04151","title":"Apollo: Unified Multi-Task Audio-Video Joint Generation","created":"2026-01-07","cited_by_count":10,"area":null},{"id":"2505.19314","title":"SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline","created":"2025-05-25","cited_by_count":9,"area":null},{"id":"2506.18729","title":"MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners","created":"2025-06-23","cited_by_count":9,"area":null},{"id":"2510.12581","title":"LayerSync: Self-aligning Intermediate Layers","created":"2025-10-14","cited_by_count":9,"area":"diffusion"},{"id":"2412.20378","title":"Tri-Ergon: Fine-grained Video-to-Audio Generation with Multi-modal Conditions and LUFS Control","created":"2024-12-29","cited_by_count":8,"area":null},{"id":"2507.20900","title":"Music Arena: Live Evaluation for Text-to-Music","created":"2025-07-28","cited_by_count":8,"area":null},{"id":"2512.12196","title":"AutoMV: An Automatic Multi-Agent System for Music Video Generation","created":"2025-12-13","cited_by_count":8,"area":null},{"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":"2507.03599","title":"MusGO: A Community-Driven Framework For Assessing Openness in Music-Generative AI","created":"2025-07-04","cited_by_count":7,"area":null},{"id":"2510.23802","title":"Learning Interpretable Features in Audio Latent Spaces via Sparse Autoencoders","created":"2025-10-27","cited_by_count":7,"area":"mechinterp"},{"id":"2511.13219","title":"FoleyBench: A Benchmark For Video-to-Audio Models","created":"2025-11-17","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":"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":"2412.09428","title":"Multimodal Music Generation with Explicit Bridges and Retrieval Augmentation","created":"2024-12-12","cited_by_count":6,"area":null},{"id":"2503.08307","title":"$^R$FLAV: Rolling Flow matching for infinite Audio Video generation","created":"2025-03-11","cited_by_count":6,"area":"diffusion"},{"id":"2504.09381","title":"DiTSE: High-Fidelity Generative Speech Enhancement via Latent Diffusion Transformers","created":"2025-04-13","cited_by_count":6,"area":"diffusion"},{"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":"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":"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":"2603.22677","title":"MuQ-Eval: An Open-Source Per-Sample Quality Metric for AI Music Generation Evaluation","created":"2026-03-24","cited_by_count":6,"area":null},{"id":"2412.15023","title":"FolAI: Synchronized Foley Sound Generation with Semantic and Temporal Alignment","created":"2024-12-19","cited_by_count":5,"area":null},{"id":"2502.04230","title":"XAttnMark: Learning Robust Audio Watermarking with Cross-Attention","created":"2025-02-06","cited_by_count":5,"area":null},{"id":"2505.16195","title":"SpecMaskFoley: Steering Pretrained Spectral Masked Generative Transformer Toward Synchronized Video-to-audio Synthesis via ControlNet","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2506.00681","title":"Learning to Upsample and Upmix Audio in the Latent Domain","created":"2025-05-31","cited_by_count":5,"area":"diffusion"},{"id":"2509.23727","title":"AudioMoG: Guiding Audio Generation with Mixture-of-Guidance","created":"2025-09-28","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":"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":"2601.08828","title":"Motion Attribution for Video Generation","created":"2026-01-13","cited_by_count":5,"area":null},{"id":"2603.00610","title":"CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction","created":"2026-02-28","cited_by_count":5,"area":"alignment"},{"id":"2501.05631","title":"HFMF: Hierarchical Fusion Meets Multi-Stream Models for Deepfake Detection","created":"2025-01-10","cited_by_count":4,"area":null},{"id":"2503.21254","title":"Vision-to-Music Generation: A Survey","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2504.04751","title":"Unsupervised Estimation of Nonlinear Audio Effects: Comparing Diffusion-Based and Adversarial approaches","created":"2025-04-07","cited_by_count":4,"area":"diffusion"},{"id":"2504.15217","title":"DRAGON: Distributional Rewards Optimize Diffusion Generative Models","created":"2025-04-21","cited_by_count":4,"area":"diffusion"},{"id":"2505.23305","title":"MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction","created":"2025-05-29","cited_by_count":4,"area":"diffusion"},{"id":"2505.23625","title":"ZeroSep: Separate Anything in Audio with Zero Training","created":"2025-05-29","cited_by_count":4,"area":"diffusion"},{"id":"2507.07867","title":"Re-Bottleneck: Latent Re-Structuring for Neural Audio Autoencoders","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2510.13344","title":"UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity MoE","created":"2025-10-15","cited_by_count":4,"area":"moe"},{"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":"2511.00103","title":"FreeSliders: Training-Free, Modality-Agnostic Concept Sliders for Fine-Grained Diffusion Control in Images, Audio, and Video","created":"2025-10-30","cited_by_count":4,"area":"diffusion"},{"id":"2602.09233","title":"Gencho: Room Impulse Response Generation from Reverberant Speech and Text via Diffusion Transformers","created":"2026-02-09","cited_by_count":4,"area":"diffusion"},{"id":"2602.11910","title":"TADA! Tuning Audio Diffusion Models through Activation Steering","created":"2026-02-12","cited_by_count":4,"area":"diffusion"},{"id":"2606.03183","title":"Inference-Time Scaling for Joint Audio-Video Generation","created":"2026-06-02","cited_by_count":4,"area":"lr"},{"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":"2509.24773","title":"VSSFlow: Unifying Video-conditioned Sound and Speech Generation via Joint Learning","created":"2025-09-29","cited_by_count":3,"area":"diffusion"},{"id":"2510.00313","title":"Post-Training Quantization for Audio Diffusion Transformers","created":"2025-09-30","cited_by_count":3,"area":"diffusion"},{"id":"2512.02650","title":"Hear What Matters! Text-conditioned Selective Video-to-Audio Generation","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2605.06407","title":"WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2605.18613","title":"SAME: A Semantically-Aligned Music Autoencoder","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2412.09405","title":"Learned Compression for Compressed Learning","created":"2024-12-12","cited_by_count":2,"area":null},{"id":"2505.07615","title":"Diffused Responsibility: Analyzing the Energy Consumption of Generative Text-to-Audio Diffusion Models","created":"2025-05-12","cited_by_count":2,"area":"diffusion"},{"id":"2506.08570","title":"Auto-Regressive vs Flow-Matching: a Comparative Study of Modeling Paradigms for Text-to-Music Generation","created":"2025-06-10","cited_by_count":2,"area":"diffusion"},{"id":"2506.18488","title":"AI-Generated Song Detection via Lyrics Transcripts","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2507.06674","title":"Exploring State-Space-Model based Language Model in Music Generation","created":"2025-07-09","cited_by_count":2,"area":"ssm"},{"id":"2508.11326","title":"MoE-TTS: Enhancing Out-of-Domain Text Understanding for Description-based TTS via Mixture-of-Experts","created":"2025-08-15","cited_by_count":2,"area":"moe"},{"id":"2509.06027","title":"DreamAudio: Customized Text-to-Audio Generation with Diffusion Models","created":"2025-09-07","cited_by_count":2,"area":"diffusion"},{"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":"2512.11348","title":"PhraseVAE and PhraseLDM: Latent Diffusion for Full-Song Multitrack Symbolic Music Generation","created":"2025-12-12","cited_by_count":2,"area":"diffusion"},{"id":"2602.03023","title":"Rethinking Music Captioning with Music Metadata LLMs","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2602.06823","title":"AI-Generated Music Detection in Broadcast Monitoring","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2603.04366","title":"Low-Resource Guidance for Controllable Latent Audio Diffusion","created":"2026-03-04","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":"2603.19176","title":"Few-shot Acoustic Synthesis with Multimodal Flow Matching","created":"2026-03-19","cited_by_count":2,"area":"diffusion"},{"id":"2504.03329","title":"Mind the Prompt: Prompting Strategies in Audio Generations for Improving Sound Classification","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2506.03530","title":"How Far Are We from Generating Missing Modalities with Foundation Models?","created":"2025-06-04","cited_by_count":1,"area":null},{"id":"2506.08457","title":"Audio Generation Through Score-Based Generative Modeling: Design Principles and Implementation","created":"2025-06-10","cited_by_count":1,"area":"diffusion"},{"id":"2507.04864","title":"Music Boomerang: Reusing Diffusion Models for Data Augmentation and Audio Manipulation","created":"2025-07-07","cited_by_count":1,"area":"diffusion"}],"next_cursor":"100"}