{"total":54,"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":"2407.01494","title":"FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds","created":"2024-07-01","cited_by_count":110,"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":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28,"area":null},{"id":"2406.08203","title":"LAFMA: A Latent Flow Matching Model for Text-to-Audio Generation","created":"2024-06-12","cited_by_count":24,"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":"2405.17842","title":"MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation","created":"2024-05-28","cited_by_count":23,"area":"diffusion"},{"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":"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":"2406.15487","title":"Improving Text-To-Audio Models with Synthetic Captions","created":"2024-06-18","cited_by_count":19,"area":null},{"id":"2402.00744","title":"BATON: Aligning Text-to-Audio Model with Human Preference Feedback","created":"2024-02-01","cited_by_count":18,"area":"alignment"},{"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":"2506.10036","title":"Token Perturbation Guidance for Diffusion Models","created":"2025-06-10","cited_by_count":15,"area":"diffusion"},{"id":"2408.02503","title":"UnifiedMLLM: Enabling Unified Representation for Multi-modal Multi-tasks With Large Language Model","created":"2024-08-05","cited_by_count":13,"area":"mllm"},{"id":"2409.12466","title":"AudioEditor: A Training-Free Diffusion-Based Audio Editing Framework","created":"2024-09-19","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":"2406.06612","title":"SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound","created":"2024-06-06","cited_by_count":10,"area":null},{"id":"2408.06849","title":"Causal Agent based on Large Language Model","created":"2024-08-13","cited_by_count":10,"area":"agents"},{"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":"2503.06984","title":"Synchronized Video-to-Audio Generation via Mel Quantization-Continuum Decomposition","created":"2025-03-10","cited_by_count":10,"area":null},{"id":"2410.03335","title":"Audio-Agent: Leveraging LLMs For Audio Generation, Editing and Composition","created":"2024-10-04","cited_by_count":9,"area":"agents"},{"id":"2510.04577","title":"Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers","created":"2025-10-06","cited_by_count":8,"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":"2503.08307","title":"$^R$FLAV: Rolling Flow matching for infinite Audio Video generation","created":"2025-03-11","cited_by_count":6,"area":"diffusion"},{"id":"2412.09168","title":"YingSound: Video-Guided Sound Effects Generation with Multi-modal Chain-of-Thought Controls","created":"2024-12-12","cited_by_count":5,"area":null},{"id":"2502.18186","title":"Steering Language Model to Stable Speech Emotion Recognition via Contextual Perception and Chain of Thought","created":"2025-02-25","cited_by_count":5,"area":"lr"},{"id":"2504.02011","title":"Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression","created":"2025-04-02","cited_by_count":5,"area":"diffusion"},{"id":"2503.07217","title":"ReelWave: Multi-Agentic Movie Sound Generation through Multimodal LLM Conversation","created":"2025-03-10","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":"2510.22795","title":"SAO-Instruct: Free-form Audio Editing using Natural Language Instructions","created":"2025-10-26","cited_by_count":4,"area":null},{"id":"2412.18157","title":"Smooth-Foley: Creating Continuous Sound for Video-to-Audio Generation Under Semantic Guidance","created":"2024-12-24","cited_by_count":3,"area":null},{"id":"2501.07766","title":"Large Language Models for Knowledge Graph Embedding: A Survey","created":"2025-01-14","cited_by_count":3,"area":null},{"id":"2501.14680","title":"Diffusion based Text-to-Music Generation with Global and Local Text based Conditioning","created":"2025-01-24","cited_by_count":3,"area":"diffusion"},{"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":"2509.14003","title":"RFM-Editing: Rectified Flow Matching for Text-guided Audio Editing","created":"2025-09-17","cited_by_count":3,"area":"diffusion"},{"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":"2505.22106","title":"AudioTurbo: Fast Text-to-Audio Generation with Rectified Diffusion","created":"2025-05-28","cited_by_count":2,"area":"diffusion"},{"id":"2506.02858","title":"DGMO: Training-Free Audio Source Separation through Diffusion-Guided Mask Optimization","created":"2025-06-03","cited_by_count":2,"area":"diffusion"},{"id":"2512.21775","title":"Compliance Rating Scheme: A Data Provenance Framework for Generative AI Datasets","created":"2025-12-25","cited_by_count":2,"area":null},{"id":"2601.14304","title":"Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding","created":"2026-01-18","cited_by_count":2,"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":"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":"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":"2507.05666","title":"Knowledge-guided Complex Diffusion Model for PolSAR Image Classification in Contourlet Domain","created":"2025-07-08","cited_by_count":0,"area":"diffusion"},{"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},{"id":"2511.04376","title":"MusRec: Zero-Shot Text-to-Music Editing via Rectified Flow and Diffusion Transformers","created":"2025-11-06","cited_by_count":0,"area":"diffusion"},{"id":"2605.30965","title":"ImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation Alignment","created":"2026-05-29","cited_by_count":0,"area":"diffusion"},{"id":"2606.09098","title":"HoliDubber: Holistic Video Dubbing for Complex Acoustic Scenes via Text-Guided Audio Synthesis","created":"2026-06-08","cited_by_count":0,"area":"diffusion"},{"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":"2607.17526","title":"FlowSonic: Stable Zero-Shot Music Editing via High-Order Trajectory Integration","created":"2026-07-20","cited_by_count":0,"area":"diffusion"},{"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":"2608.04479","title":"AudioScape-TTA: A Structured Soundscape Benchmark for Fine-Grained Text-to-Audio Evaluation","created":"2026-08-05","cited_by_count":0,"area":null}],"next_cursor":null}