{"total":47,"rows":[{"id":"2407.14358","title":"Stable Audio Open","created":"2024-07-19","cited_by_count":197,"area":null},{"id":"2408.01337","title":"MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models","created":"2024-08-02","cited_by_count":44,"area":null},{"id":"2505.15957","title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","created":"2025-05-21","cited_by_count":39,"area":null},{"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":"2502.07461","title":"JamendoMaxCaps: A Large Scale Music-caption Dataset with Imputed Metadata","created":"2025-02-11","cited_by_count":15,"area":null},{"id":"2509.17609","title":"Audio Super-Resolution with Latent Bridge Models","created":"2025-09-22","cited_by_count":14,"area":null},{"id":"2410.13267","title":"CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Models","created":"2024-10-17","cited_by_count":12,"area":null},{"id":"2506.11350","title":"GLAP: General contrastive audio-text pretraining across domains and languages","created":"2025-06-12","cited_by_count":10,"area":null},{"id":"2508.04651","title":"Live Music Models","created":"2025-08-06","cited_by_count":10,"area":null},{"id":"2410.06084","title":"Diversity-Rewarded CFG Distillation","created":"2024-10-08","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":"2404.07616","title":"Audio Dialogues: Dialogues dataset for audio and music understanding","created":"2024-04-11","cited_by_count":7,"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":"2507.23511","title":"MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks","created":"2025-07-31","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":"2409.11449","title":"Evaluation of pretrained language models on music understanding","created":"2024-09-17","cited_by_count":4,"area":null},{"id":"2410.02271","title":"CoLLAP: Contrastive Long-form Language-Audio Pretraining with Musical Temporal Structure Augmentation","created":"2024-10-03","cited_by_count":4,"area":null},{"id":"2507.07867","title":"Re-Bottleneck: Latent Re-Structuring for Neural Audio Autoencoders","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2409.11498","title":"Augment, Drop & Swap: Improving Diversity in LLM Captions for Efficient Music-Text Representation Learning","created":"2024-09-17","cited_by_count":3,"area":null},{"id":"2410.13114","title":"Sound Check: Auditing Audio Datasets","created":"2024-10-17","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":"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":"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":"2409.03844","title":"MetaBGM: Dynamic Soundtrack Transformation For Continuous Multi-Scene Experiences With Ambient Awareness And Personalization","created":"2024-09-05","cited_by_count":1,"area":null},{"id":"2602.21772","title":"UniWhisper: Efficient Continual Multi-task Training for Robust Universal Audio Representation","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2603.27877","title":"HumMusQA: A Human-written Music Understanding QA Benchmark Dataset","created":"2026-03-29","cited_by_count":1,"area":null},{"id":"2605.15831","title":"Modeling Music as a Time-Frequency Image: A 2D Tokenizer for Music Generation","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2509.16418","title":"LenslessMic: Audio Encryption and Authentication via Lensless Computational Imaging","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2601.14157","title":"ConceptCaps: a Distilled Concept Dataset for Interpretability in Music Models","created":"2026-01-20","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":"2602.11941","title":"IncompeBench: A Permissively Licensed, Fine-Grained Benchmark for Music Information Retrieval","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2604.07895","title":"DialBGM: A Benchmark for Background Music Recommendation from Everyday Multi-Turn Dialogues","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2606.24307","title":"Real-Time Interactive Music Generation via Data-Free Streaming Consistency Distillation","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2606.27320","title":"Elastic Time: Dynamic Frame Rate Bottlenecks for Neural Audio Coding","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.05198","title":"Noisy-Channel Minimum Bayes Risk Decoding","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2609.04362","title":"Knowing When Not to Answer: Pseudo-Ensembles for Abstention in Music Audio-Language Models","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.14820","title":"POLARIS: Training-Free Audio Fingerprinting with Saliency-Based Landmarks and Delaunay Grouping","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.16090","title":"MUUNRiver-Bench: Diagnosing Relation-Dependent Music Retrieval with Multimodal Instructions","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.18041","title":"Correlation-Guided Encoder Selection for Multi-Encoder Large Audio-Language Models","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.20195","title":"Music Hallucination in Audio-Language Models: A Hierarchical Formulation and Empirical Study","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2609.22851","title":"Discrete vs. Continuous: A Comprehensive Study of Unified Audio Understanding in LALMs","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.30540","title":"Don't CLAP: Are Music-Text Models Bag-of-Words?","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.32755","title":"SAGE: Semantic Audio Generative Encoder","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33893","title":"MISHAP-Bench: A Hallucination Benchmark for Large Audio-Language Models","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}