{"total":173,"rows":[{"id":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488,"area":null},{"id":"2305.02463","title":"Shap-E: Generating Conditional 3D Implicit Functions","created":"2023-05-03","cited_by_count":385,"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":"2309.15807","title":"Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack","created":"2023-09-27","cited_by_count":279,"area":null},{"id":"2303.09556","title":"Efficient Diffusion Training via Min-SNR Weighting Strategy","created":"2023-03-16","cited_by_count":246,"area":"diffusion"},{"id":"2303.11989","title":"Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models","created":"2023-03-21","cited_by_count":245,"area":null},{"id":"2402.04825","title":"Fast Timing-Conditioned Latent Audio Diffusion","created":"2024-02-07","cited_by_count":181,"area":null},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157,"area":null},{"id":"2310.17347","title":"CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling","created":"2023-10-26","cited_by_count":129,"area":"diffusion"},{"id":"2312.15821","title":"Audiobox: Unified Audio Generation with Natural Language Prompts","created":"2023-12-25","cited_by_count":120,"area":"diffusion"},{"id":"2410.02416","title":"Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models","created":"2024-10-03","cited_by_count":114,"area":"diffusion"},{"id":"2305.01115","title":"In-Context Learning Unlocked for Diffusion Models","created":"2023-05-01","cited_by_count":104,"area":"diffusion"},{"id":"2306.09329","title":"DreamHuman: Animatable 3D Avatars from Text","created":"2023-06-15","cited_by_count":102,"area":null},{"id":"2308.01546","title":"MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies","created":"2023-08-03","cited_by_count":94,"area":"diffusion"},{"id":"2404.10301","title":"Long-form music generation with latent diffusion","created":"2024-04-16","cited_by_count":89,"area":"diffusion"},{"id":"2307.07947","title":"Language Conditioned Traffic Generation","created":"2023-07-16","cited_by_count":87,"area":null},{"id":"2304.00830","title":"AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models","created":"2023-04-03","cited_by_count":83,"area":"diffusion"},{"id":"2401.12179","title":"DITTO: Diffusion Inference-Time T-Optimization for Music Generation","created":"2024-01-22","cited_by_count":73,"area":"diffusion"},{"id":"2311.10057","title":"The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation","created":"2023-11-16","cited_by_count":68,"area":null},{"id":"2401.08639","title":"One-Step Diffusion Distillation via Deep Equilibrium Models","created":"2023-12-12","cited_by_count":61,"area":"diffusion"},{"id":"2306.04542","title":"On the Design Fundamentals of Diffusion Models: A Survey","created":"2023-06-07","cited_by_count":60,"area":"diffusion"},{"id":"2402.14285","title":"Symbolic Music Generation with Non-Differentiable Rule Guided Diffusion","created":"2024-02-22","cited_by_count":54,"area":"diffusion"},{"id":"2407.02687","title":"No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models","created":"2024-07-02","cited_by_count":53,"area":"diffusion"},{"id":"2306.00110","title":"MuseCoco: Generating Symbolic Music from Text","created":"2023-05-31","cited_by_count":52,"area":null},{"id":"2305.15719","title":"Efficient Neural Music Generation","created":"2023-05-25","cited_by_count":50,"area":null},{"id":"2309.01700","title":"ControlMat: A Controlled Generative Approach to Material Capture","created":"2023-09-04","cited_by_count":50,"area":"diffusion"},{"id":"2401.04577","title":"Masked Audio Generation using a Single Non-Autoregressive Transformer","created":"2024-01-09","cited_by_count":50,"area":null},{"id":"2308.09716","title":"Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization","created":"2023-08-18","cited_by_count":49,"area":"diffusion"},{"id":"2303.15780","title":"Instruct 3D-to-3D: Text Instruction Guided 3D-to-3D conversion","created":"2023-03-28","cited_by_count":48,"area":null},{"id":"2308.04729","title":"JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models","created":"2023-08-09","cited_by_count":41,"area":"diffusion"},{"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":"2406.03293","title":"Text-to-Image Rectified Flow as Plug-and-Play Priors","created":"2024-06-05","cited_by_count":38,"area":"diffusion"},{"id":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37,"area":"diffusion"},{"id":"2306.08620","title":"Anticipatory Music Transformer","created":"2023-06-14","cited_by_count":36,"area":null},{"id":"2411.05679","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","created":"2024-11-08","cited_by_count":34,"area":null},{"id":"2406.08384","title":"Diff-A-Riff: Musical Accompaniment Co-creation via Latent Diffusion Models","created":"2024-06-12","cited_by_count":33,"area":"diffusion"},{"id":"2312.08723","title":"StemGen: A music generation model that listens","created":"2023-12-14","cited_by_count":32,"area":null},{"id":"2402.04229","title":"MusicRL: Aligning Music Generation to Human Preferences","created":"2024-02-06","cited_by_count":32,"area":"alignment"},{"id":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"area":null},{"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":"2308.12350","title":"Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentation","created":"2023-08-23","cited_by_count":27,"area":"diffusion"},{"id":"2306.00974","title":"Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Search","created":"2023-06-01","cited_by_count":25,"area":"diffusion"},{"id":"2308.14360","title":"InstructME: An Instruction Guided Music Edit And Remix Framework with Latent Diffusion Models","created":"2023-08-28","cited_by_count":23,"area":"diffusion"},{"id":"2308.02560","title":"From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion","created":"2023-08-02","cited_by_count":22,"area":null},{"id":"2309.10740","title":"ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation","created":"2023-09-19","cited_by_count":22,"area":"diffusion"},{"id":"2312.07539","title":"HeadArtist: Text-conditioned 3D Head Generation with Self Score Distillation","created":"2023-12-12","cited_by_count":22,"area":null},{"id":"2405.14477","title":"LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models","created":"2024-05-23","cited_by_count":22,"area":"diffusion"},{"id":"2409.03550","title":"DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture","created":"2024-09-05","cited_by_count":22,"area":"diffusion"},{"id":"2306.01433","title":"Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approach","created":"2023-06-02","cited_by_count":21,"area":null},{"id":"2312.03584","title":"Context Diffusion: In-Context Aware Image Generation","created":"2023-12-06","cited_by_count":21,"area":null},{"id":"2306.09635","title":"CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models","created":"2023-06-16","cited_by_count":20,"area":"diffusion"},{"id":"2310.17162","title":"Content-based Controls For Music Large Language Modeling","created":"2023-10-26","cited_by_count":19,"area":null},{"id":"2405.15388","title":"Language-Driven Interactive Traffic Trajectory Generation","created":"2024-05-24","cited_by_count":19,"area":null},{"id":"2406.02255","title":"MidiCaps: A large-scale MIDI dataset with text captions","created":"2024-06-04","cited_by_count":19,"area":null},{"id":"2406.04673","title":"MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models","created":"2024-06-07","cited_by_count":19,"area":"diffusion"},{"id":"2410.04534","title":"UniMuMo: Unified Text, Music and Motion Generation","created":"2024-10-06","cited_by_count":19,"area":null},{"id":"2412.16526","title":"Text2midi: Generating Symbolic Music from Captions","created":"2024-12-21","cited_by_count":19,"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":"2409.00587","title":"FLUX that Plays Music","created":"2024-09-01","cited_by_count":18,"area":"diffusion"},{"id":"2305.01319","title":"Long-Term Rhythmic Video Soundtracker","created":"2023-05-02","cited_by_count":17,"area":null},{"id":"2310.19180","title":"JEN-1 Composer: A Unified Framework for High-Fidelity Multi-Track Music Generation","created":"2023-10-29","cited_by_count":17,"area":null},{"id":"2310.19789","title":"DiffEnc: Variational Diffusion with a Learned Encoder","created":"2023-10-30","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":"2501.06250","title":"Generative AI for Cel-Animation: A Survey","created":"2025-01-08","cited_by_count":17,"area":null},{"id":"2402.09871","title":"MuChin: A Chinese Colloquial Description Benchmark for Evaluating Language Models in the Field of Music","created":"2024-02-15","cited_by_count":16,"area":null},{"id":"2410.05167","title":"Presto! Distilling Steps and Layers for Accelerating Music Generation","created":"2024-10-07","cited_by_count":16,"area":"diffusion"},{"id":"2302.04456","title":"ERNIE-Music: Text-to-Waveform Music Generation with Diffusion Models","created":"2023-02-09","cited_by_count":15,"area":"diffusion"},{"id":"2311.08667","title":"EDMSound: Spectrogram Based Diffusion Models for Efficient and High-Quality Audio Synthesis","created":"2023-11-15","cited_by_count":15,"area":"diffusion"},{"id":"2402.01369","title":"On the Multi-modal Vulnerability of Diffusion Models","created":"2024-02-02","cited_by_count":15,"area":"diffusion"},{"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":"2410.20478","title":"MusicFlow: Cascaded Flow Matching for Text Guided Music Generation","created":"2024-10-27","cited_by_count":15,"area":null},{"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":"2506.19085","title":"Benchmarking Music Generation Models and Metrics via Human Preference Studies","created":"2025-06-23","cited_by_count":15,"area":null},{"id":"2506.19713","title":"Guidance in the Frequency Domain Enables High-Fidelity Sampling at Low CFG Scales","created":"2025-06-24","cited_by_count":15,"area":"diffusion"},{"id":"2410.12957","title":"MuVi: Video-to-Music Generation with Semantic Alignment and Rhythmic Synchronization","created":"2024-10-16","cited_by_count":14,"area":null},{"id":"2503.19611","title":"Analyzable Chain-of-Musical-Thought Prompting for High-Fidelity Music Generation","created":"2025-03-25","cited_by_count":14,"area":null},{"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":"2509.17609","title":"Audio Super-Resolution with Latent Bridge Models","created":"2025-09-22","cited_by_count":14,"area":null},{"id":"2306.13512","title":"DISCO-10M: A Large-Scale Music Dataset","created":"2023-06-23","cited_by_count":13,"area":null},{"id":"2407.03648","title":"High Fidelity Text-Guided Music Editing via Single-Stage Flow Matching","created":"2024-07-04","cited_by_count":13,"area":"diffusion"},{"id":"2407.16564","title":"Audio Prompt Adapter: Unleashing Music Editing Abilities for Text-to-Music with Lightweight Finetuning","created":"2024-07-23","cited_by_count":12,"area":null},{"id":"2409.06029","title":"SongCreator: Lyrics-based Universal Song Generation","created":"2024-09-09","cited_by_count":12,"area":null},{"id":"2602.21185","title":"The Diffusion Duality, Chapter II: $\\Psi$-Samplers","created":"2026-02-24","cited_by_count":12,"area":"diffusion"},{"id":"2310.03015","title":"Efficient-3DiM: Learning a Generalizable Single-image Novel-view Synthesizer in One Day","created":"2023-10-04","cited_by_count":11,"area":"diffusion"},{"id":"2407.15060","title":"MusiConGen: Rhythm and Chord Control for Transformer-Based Text-to-Music Generation","created":"2024-07-21","cited_by_count":11,"area":null},{"id":"2307.11078","title":"Brain2Music: Reconstructing Music from Human Brain Activity","created":"2023-07-20","cited_by_count":10,"area":null},{"id":"2310.10604","title":"Generation or Replication: Auscultating Audio Latent Diffusion Models","created":"2023-10-16","cited_by_count":10,"area":"diffusion"},{"id":"2402.13763","title":"Music Style Transfer with Time-Varying Inversion of Diffusion Models","created":"2024-02-21","cited_by_count":10,"area":"diffusion"},{"id":"2404.13320","title":"Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Think","created":"2024-04-20","cited_by_count":10,"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":"2408.00196","title":"Combining audio control and style transfer using latent diffusion","created":"2024-07-31","cited_by_count":10,"area":"diffusion"},{"id":"2502.21318","title":"How far can we go with ImageNet for Text-to-Image generation?","created":"2025-02-28","cited_by_count":10,"area":null},{"id":"2308.12982","title":"A Survey of AI Music Generation Tools and Models","created":"2023-08-24","cited_by_count":9,"area":null},{"id":"2406.00856","title":"DistilDIRE: A Small, Fast, Cheap and Lightweight Diffusion Synthesized Deepfake Detection","created":"2024-06-02","cited_by_count":9,"area":"diffusion"},{"id":"2407.02049","title":"Accompanied Singing Voice Synthesis with Fully Text-controlled Melody","created":"2024-07-02","cited_by_count":9,"area":null},{"id":"2410.06084","title":"Diversity-Rewarded CFG Distillation","created":"2024-10-08","cited_by_count":9,"area":null},{"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":"2401.12570","title":"DiffMoog: a Differentiable Modular Synthesizer for Sound Matching","created":"2024-01-23","cited_by_count":7,"area":null},{"id":"2404.13358","title":"Music Consistency Models","created":"2024-04-20","cited_by_count":7,"area":"diffusion"},{"id":"2405.02801","title":"Mozart's Touch: A Lightweight Multi-modal Music Generation Framework Based on Pre-Trained Large Models","created":"2024-05-05","cited_by_count":7,"area":null}],"next_cursor":"100"}