{"total":100,"rows":[{"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":"2503.03983","title":"Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities","created":"2025-03-06","cited_by_count":133,"area":"lr"},{"id":"2505.13032","title":"MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix","created":"2025-05-19","cited_by_count":117,"area":"lr"},{"id":"2404.09956","title":"Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization","created":"2024-04-15","cited_by_count":97,"area":"diffusion"},{"id":"2503.02318","title":"Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models","created":"2025-03-04","cited_by_count":95,"area":"lr"},{"id":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37,"area":"diffusion"},{"id":"2504.15900","title":"SARI: Structured Audio Reasoning via Curriculum-Guided Reinforcement Learning","created":"2025-04-22","cited_by_count":34,"area":"lr"},{"id":"2402.06178","title":"MusicMagus: Zero-Shot Text-to-Music Editing via Diffusion Models","created":"2024-02-09","cited_by_count":32,"area":"diffusion"},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28,"area":null},{"id":"2511.12609","title":"Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data","created":"2025-11-16","cited_by_count":21,"area":"moe"},{"id":"2406.02255","title":"MidiCaps: A large-scale MIDI dataset with text captions","created":"2024-06-04","cited_by_count":19,"area":null},{"id":"2406.15487","title":"Improving Text-To-Audio Models with Synthetic Captions","created":"2024-06-18","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":"2604.10905","title":"Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music","created":"2026-04-13","cited_by_count":19,"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":"2506.12285","title":"CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following","created":"2025-06-14","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":"2405.18386","title":"Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuning","created":"2024-05-28","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":"2508.02018","title":"SpeechR: A Benchmark for Speech Reasoning in Large Audio-Language Models","created":"2025-08-04","cited_by_count":14,"area":"lr"},{"id":"2409.12346","title":"Simultaneous Music Separation and Generation Using Multi-Track Latent Diffusion Models","created":"2024-09-18","cited_by_count":13,"area":"diffusion"},{"id":"2505.18186","title":"Discovering and Steering Interpretable Concepts in Large Generative Music Models","created":"2025-05-18","cited_by_count":13,"area":"mechinterp"},{"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":"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":"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":"2505.13115","title":"Benchmarking and Confidence Evaluation of LALMs For Temporal Reasoning","created":"2025-05-19","cited_by_count":10,"area":"lr"},{"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":"2506.18729","title":"MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners","created":"2025-06-23","cited_by_count":9,"area":null},{"id":"2404.13358","title":"Music Consistency Models","created":"2024-04-20","cited_by_count":7,"area":"diffusion"},{"id":"2406.08809","title":"Are We There Yet? A Brief Survey of Music Emotion Prediction Datasets, Models and Outstanding Challenges","created":"2024-06-13","cited_by_count":7,"area":null},{"id":"2508.03448","title":"SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering","created":"2025-08-05","cited_by_count":6,"area":null},{"id":"2510.19127","title":"Steering Autoregressive Music Generation with Recursive Feature Machines","created":"2025-10-21","cited_by_count":6,"area":null},{"id":"2407.20445","title":"Futga: Towards Fine-grained Music Understanding through Temporally-enhanced Generative Augmentation","created":"2024-07-29","cited_by_count":5,"area":null},{"id":"2409.02845","title":"Multi-Track MusicLDM: Towards Versatile Music Generation with Latent Diffusion Model","created":"2024-09-04","cited_by_count":5,"area":"diffusion"},{"id":"2506.10574","title":"DanceChat: Large Language Model-Guided Music-to-Dance Generation","created":"2025-06-12","cited_by_count":5,"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":"2502.07328","title":"Music for All: Representational Bias and Cross-Cultural Adaptability of Music Generation Models","created":"2025-02-11","cited_by_count":4,"area":null},{"id":"2502.14893","title":"NOTA: Multimodal Music Notation Understanding for Visual Large Language Model","created":"2025-02-17","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":"2504.13535","title":"MusFlow: Multimodal Music Generation via Conditional Flow Matching","created":"2025-04-18","cited_by_count":4,"area":"diffusion"},{"id":"2505.12669","title":"Text2midi-InferAlign: Improving Symbolic Music Generation with Inference-Time Alignment","created":"2025-05-19","cited_by_count":4,"area":null},{"id":"2505.15559","title":"Moonbeam: A MIDI Foundation Model Using Both Absolute and Relative Music Attributes","created":"2025-05-21","cited_by_count":4,"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":"2412.04100","title":"Missing Melodies: AI Music Generation and its \"Nearly\" Complete Omission of the Global South","created":"2024-12-05","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":"2505.20979","title":"MelodySim: Measuring Melody-aware Music Similarity for Plagiarism Detection","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2506.17886","title":"GD-Retriever: Controllable Generative Text-Music Retrieval with Diffusion Models","created":"2025-06-22","cited_by_count":3,"area":"diffusion"},{"id":"2507.20627","title":"Controllable Video-to-Music Generation with Multiple Time-Varying Conditions","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2606.03116","title":"AnyAudio-Judge: A Dynamic Rubric-Based Benchmark and Evaluator for Audio Instruction Following","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2407.03188","title":"MuDiT & MuSiT: Alignment with Colloquial Expression in Description-to-Song Generation","created":"2024-07-03","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":"2601.20028","title":"Decomposing multimodal embedding spaces with group-sparse autoencoders","created":"2026-01-27","cited_by_count":2,"area":"mechinterp"},{"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":"2604.22209","title":"UniSonate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions","created":"2026-04-24","cited_by_count":2,"area":"diffusion"},{"id":"2407.10328","title":"The Interpretation Gap in Text-to-Music Generation Models","created":"2024-07-14","cited_by_count":1,"area":null},{"id":"2409.09378","title":"Prevailing Research Areas for Music AI in the Era of Foundation Models","created":"2024-09-14","cited_by_count":1,"area":null},{"id":"2503.00957","title":"Exploiting Vulnerabilities in Speech Translation Systems through Targeted Adversarial Attacks","created":"2025-03-02","cited_by_count":1,"area":null},{"id":"2506.10225","title":"Genre Controlled Music Generation via Activation Steering","created":"2025-06-11","cited_by_count":1,"area":null},{"id":"2509.08283","title":"Segment Transformer: AI-Generated Music Detection via Music Structural Analysis","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2602.13954","title":"Eureka-Audio: Triggering Audio Intelligence in Compact Language Models","created":"2026-02-15","cited_by_count":1,"area":"moe"},{"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":"2606.25391","title":"From Sounds to Scenes: A Benchmark for Evaluating Context-Aware Auditory Scene Understanding in Large Audio Language Models","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2412.08944","title":"Interpreting Graphic Notation with MusicLDM: An AI Improvisation of Cornelius Cardew's Treatise","created":"2024-12-12","cited_by_count":0,"area":null},{"id":"2506.10754","title":"BNMusic: Blending Environmental Noises into Personalized Music","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2506.15154","title":"SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning","created":"2025-06-18","cited_by_count":0,"area":null},{"id":"2506.21298","title":"Exploring Adapter Design Tradeoffs for Low Resource Music Generation","created":"2025-06-26","cited_by_count":0,"area":null},{"id":"2508.20665","title":"Amadeus: Autoregressive Model with Bidirectional Attribute Modelling for Symbolic Music","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2509.00813","title":"AImoclips: A Benchmark for Evaluating Emotion Conveyance in Text-to-Music Generation","created":"2025-08-31","cited_by_count":0,"area":null},{"id":"2509.00914","title":"TinyMusician: On-Device Music Generation with Knowledge Distillation and Mixed Precision Quantization","created":"2025-08-31","cited_by_count":0,"area":null},{"id":"2509.09717","title":"Testing chatbots on the creation of encoders for audio conditioned image generation","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2509.22378","title":"Zero-Effort Image-to-Music Generation: An Interpretable RAG-based VLM Approach","created":"2025-09-26","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":"2511.15038","title":"Aligning Generative Music AI with Human Preferences: Methods and Challenges","created":"2025-11-19","cited_by_count":0,"area":"alignment"},{"id":"2601.01153","title":"SongSage: A Large Musical Language Model with Lyric Generative Pre-training","created":"2026-01-03","cited_by_count":0,"area":null},{"id":"2601.14786","title":"Training-Efficient Text-to-Music Generation with State-Space Modeling","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2602.17599","title":"Art2Mus: Artwork-to-Music Generation via Visual Conditioning and Large-Scale Cross-Modal Alignment","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.21073","title":"SqueezeComposer: Temporal Speed-up is A Simple Trick for Long-form Music Composing","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2603.27667","title":"EvA: An Evidence-First Audio Understanding Paradigm for LALMs","created":"2026-03-29","cited_by_count":0,"area":null},{"id":"2604.20719","title":"ONOTE: Hypergraph-Grounded Omnimodal Reasoning for Computational Music Science","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.01235","title":"MindMelody: A Closed-Loop EEG-Driven System for Personalized Music Intervention","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2605.29202","title":"Auditing Training Data in Generative Music Models via Black-Box Membership Inference","created":"2026-05-28","cited_by_count":0,"area":"safety"},{"id":"2605.31521","title":"UniAudio-Token: Empowering Semantic Speech Tokenizers with General Audio Perception","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.01703","title":"JenBridge: Adaptive Long-Form Video Soundtracking across Scene Transitions","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.02739","title":"EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.06615","title":"FIGMA: Towards FIne-Grained Music retrievAl","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.08425","title":"TinyGiantALM: A Compact Audio-Language Model for Intent-Aware Reasoning under Resource Constraints","created":"2026-06-07","cited_by_count":0,"area":"lr"},{"id":"2606.14591","title":"AudioDER: A Deduplication-Enhanced Reasoning Dataset for Post-Training Large Audio-Language Models","created":"2026-06-12","cited_by_count":0,"area":"lr"},{"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":"2608.03050","title":"Learning Music Style for Piano Arrangement Through Cross-Modal Bootstrapping","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.03920","title":"Equivariant Music Transformer","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.09035","title":"MusicLayout: Explicit Structural Planning for Controllable Text-to-Music Generation","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.23758","title":"EXAM2: Extending Audio Understanding in Multilingual and Multimodal Analysis","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.30125","title":"VIBE: Video Instruction-aligned Background music gEneration","created":"2026-08-31","cited_by_count":0,"area":"alignment"},{"id":"2609.04516","title":"Pitch-class Steering for Diffusion-based Music Generation via Latent-space Probes","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.14344","title":"AURA: Unified Multimodal Framework for Conversational Music Editing","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.39199","title":"UniAE-MoE: A Unified Audio Encoder via Mixture of Experts","created":"2026-09-30","cited_by_count":0,"area":"moe"},{"id":"2610.00835","title":"TrueMuse: A Benchmark for Data Attribution in Text-to-Music Models","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}