{"total":152,"rows":[{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506,"area":null},{"id":"2402.01831","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","created":"2024-02-02","cited_by_count":186,"area":null},{"id":"2408.16532","title":"WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling","created":"2024-08-29","cited_by_count":129,"area":null},{"id":"2308.11276","title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","created":"2023-08-22","cited_by_count":77,"area":null},{"id":"2408.17175","title":"Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model","created":"2024-08-30","cited_by_count":72,"area":null},{"id":"2501.01108","title":"MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization","created":"2025-01-02","cited_by_count":68,"area":null},{"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":"2309.08730","title":"MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response","created":"2023-09-15","cited_by_count":45,"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":"2306.10548","title":"MARBLE: Music Audio Representation Benchmark for Universal Evaluation","created":"2023-06-18","cited_by_count":38,"area":null},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2404.06393","title":"MuPT: A Generative Symbolic Music Pretrained Transformer","created":"2024-04-09","cited_by_count":33,"area":null},{"id":"2310.07160","title":"LLark: A Multimodal Instruction-Following Language Model for Music","created":"2023-10-11","cited_by_count":29,"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":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"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":"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":"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":"2306.17103","title":"LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT","created":"2023-06-29","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":"2410.00872","title":"Do Music Generation Models Encode Music Theory?","created":"2024-10-01","cited_by_count":13,"area":null},{"id":"2512.19687","title":"Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning","created":"2025-12-22","cited_by_count":13,"area":null},{"id":"2409.06029","title":"SongCreator: Lyrics-based Universal Song Generation","created":"2024-09-09","cited_by_count":12,"area":null},{"id":"2406.15885","title":"The Music Maestro or The Musically Challenged, A Massive Music Evaluation Benchmark for Large Language Models","created":"2024-06-22","cited_by_count":10,"area":null},{"id":"2410.15573","title":"OpenMU: Your Swiss Army Knife for Music Understanding","created":"2024-10-21","cited_by_count":9,"area":null},{"id":"2506.23869","title":"Scaling Self-Supervised Representation Learning for Symbolic Piano Performance","created":"2025-06-30","cited_by_count":9,"area":null},{"id":"2503.17340","title":"Align Your Rhythm: Generating Highly Aligned Dance Poses with Gating-Enhanced Rhythm-Aware Feature Representation","created":"2025-03-21","cited_by_count":8,"area":null},{"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":"2502.03979","title":"Towards Unified Music Emotion Recognition across Dimensional and Categorical Models","created":"2025-02-06","cited_by_count":7,"area":null},{"id":"2504.06753","title":"Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory Perception","created":"2025-04-09","cited_by_count":7,"area":null},{"id":"2506.18843","title":"USAD: Universal Speech and Audio Representation via Distillation","created":"2025-06-23","cited_by_count":7,"area":null},{"id":"2408.07851","title":"SER Evals: In-domain and Out-of-domain Benchmarking for Speech Emotion Recognition","created":"2024-08-14","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":"2508.12709","title":"MATPAC++: Enhanced Masked Latent Prediction for Self-Supervised Audio Representation Learning","created":"2025-08-18","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":"2310.10159","title":"Joint Music and Language Attention Models for Zero-shot Music Tagging","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2402.15569","title":"Toward Fully Self-Supervised Multi-Pitch Estimation","created":"2024-02-23","cited_by_count":5,"area":null},{"id":"2405.07682","title":"FastSAG: Towards Fast Non-Autoregressive Singing Accompaniment Generation","created":"2024-05-13","cited_by_count":5,"area":null},{"id":"2310.09853","title":"MERTech: Instrument Playing Technique Detection Using Self-Supervised Pretrained Model With Multi-Task Finetuning","created":"2023-10-15","cited_by_count":4,"area":null},{"id":"2401.08889","title":"On the Effect of Data-Augmentation on Local Embedding Properties in the Contrastive Learning of Music Audio Representations","created":"2024-01-17","cited_by_count":4,"area":null},{"id":"2404.09177","title":"An Experimental Comparison Of Multi-view Self-supervised Methods For Music Tagging","created":"2024-04-14","cited_by_count":4,"area":null},{"id":"2409.09601","title":"A Survey of Foundation Models for Music Understanding","created":"2024-09-15","cited_by_count":4,"area":null},{"id":"2502.12031","title":"Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2502.12489","title":"A Comprehensive Survey on Generative AI for Video-to-Music Generation","created":"2025-02-18","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":"2504.08907","title":"Spatial Audio Processing with Large Language Model on Wearable Devices","created":"2025-04-11","cited_by_count":4,"area":null},{"id":"2505.16306","title":"Layer-wise Investigation of Large-Scale Self-Supervised Music Representation Models","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2511.16757","title":"Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2403.13901","title":"Train & Constrain: Phonologically Informed Tongue-Twister Generation from Topics and Paraphrases","created":"2024-03-20","cited_by_count":3,"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":"2505.20979","title":"MelodySim: Measuring Melody-aware Music Similarity for Plagiarism Detection","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2506.17055","title":"Universal Music Representations? Evaluating Foundation Models on World Music Corpora","created":"2025-06-20","cited_by_count":3,"area":null},{"id":"2510.08062","title":"Attribution-by-design: Ensuring Inference-Time Provenance in Generative Music Systems","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2603.27314","title":"TokenDance: Token-to-Token Music-to-Dance Generation with Bidirectional Mamba","created":"2026-03-28","cited_by_count":3,"area":null},{"id":"2604.08184","title":"AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2312.06646","title":"Computational Copyright: Towards A Royalty Model for Music Generative AI","created":"2023-12-11","cited_by_count":2,"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":"2506.11403","title":"A correlation-permutation approach for speech-music encoders model merging","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2506.17818","title":"CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2506.23873","title":"Emergent musical properties of a transformer under contrastive self-supervised learning","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2507.16696","title":"FISHER: A Foundation Model for Multi-Modal Industrial Signal Comprehensive Representation","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2509.04980","title":"MAIA: An Inpainting-Based Approach for Music Adversarial Attacks","created":"2025-09-05","cited_by_count":2,"area":null},{"id":"2509.14052","title":"AnyAccomp: Generalizable Accompaniment Generation via Quantized Melodic Bottleneck","created":"2025-09-17","cited_by_count":2,"area":null},{"id":"2601.21260","title":"Music Plagiarism Detection: Problem Formulation and a Segment-based Solution","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2604.17656","title":"Video-Robin: Autoregressive Diffusion Planning for Intent-Grounded Video-to-Music Generation","created":"2026-04-19","cited_by_count":2,"area":null},{"id":"2605.29300","title":"MusTBench: Benchmarking and Advancing Temporal Grounding in Music LLMs","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2607.08168","title":"MuScriptor: An Open Model for Multi-Instrument Music Transcription","created":"2026-07-09","cited_by_count":2,"area":null},{"id":"2306.12714","title":"Toward Leveraging Pre-Trained Self-Supervised Frontends for Automatic Singing Voice Understanding Tasks: Three Case Studies","created":"2023-06-22","cited_by_count":1,"area":null},{"id":"2401.08891","title":"Tempo estimation as fully self-supervised binary classification","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2401.08902","title":"Similar but Faster: Manipulation of Tempo in Music Audio Embeddings for Tempo Prediction and Search","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2401.15323","title":"Music Auto-Tagging with Robust Music Representation Learned via Domain Adversarial Training","created":"2024-01-27","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":"2410.11522","title":"Leveraging LLM Embeddings for Cross Dataset Label Alignment and Zero Shot Music Emotion Prediction","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2502.12925","title":"Keep what you need : extracting efficient subnetworks from large audio representation models","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2503.23128","title":"CrossMuSim: A Cross-Modal Framework for Music Similarity Retrieval with LLM-Powered Text Description Sourcing and Mining","created":"2025-03-29","cited_by_count":1,"area":null},{"id":"2505.20794","title":"VibE-SVC: Vibrato Extraction with High-frequency F0 Contour for Singing Voice Conversion","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2506.23196","title":"DEL: Dense Event Localization for Multi-modal Audio-Visual Understanding","created":"2025-06-29","cited_by_count":1,"area":null},{"id":"2508.01178","title":"Advancing the Foundation Model for Music Understanding","created":"2025-08-02","cited_by_count":1,"area":null},{"id":"2509.08282","title":"Real-world Music Plagiarism Detection With Music Segment Transcription System","created":"2025-09-10","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":"2512.17209","title":"Do Foundational Audio Encoders Understand Music Structure?","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2601.13647","title":"Fusion Segment Transformer: Bi-Directional Attention Guided Fusion Network for AI-Generated Music Detection","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2603.25767","title":"Unlocking Strong Supervision: A Data-Centric Study of General-Purpose Audio Pre-Training Methods","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2605.00251","title":"Alethia: A Foundational Encoder for Voice Deepfakes","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.03929","title":"PHALAR: Phasors for Learned Musical Audio Representations","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2606.06444","title":"USAD 2.0: Scaling Representation Distillation for Universal Audio Understanding","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2607.03296","title":"Taste-aware music retrieval from audio embeddings","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2607.03806","title":"Probing Low-Level Acoustic Attribute Encoding in CLAP Audio Embeddings","created":"2026-07-04","cited_by_count":1,"area":null},{"id":"2607.10287","title":"InterPet4D: A Multimodal 4D Human-Pet Interaction Dataset for Pet Motion Generation","created":"2026-07-11","cited_by_count":1,"area":null},{"id":"2309.11895","title":"Audio Contrastive-based Fine-tuning: Decoupling Representation Learning and Classification","created":"2023-09-21","cited_by_count":0,"area":null},{"id":"2409.06690","title":"Benchmarking Sub-Genre Classification For Mainstage Dance Music","created":"2024-09-10","cited_by_count":0,"area":null},{"id":"2409.09866","title":"S2Cap: A Benchmark and a Baseline for Singing Style Captioning","created":"2024-09-15","cited_by_count":0,"area":null},{"id":"2409.14131","title":"Are Music Foundation Models Better at Singing Voice Deepfake Detection? Far-Better Fuse them with Speech Foundation Models","created":"2024-09-21","cited_by_count":0,"area":null},{"id":"2409.15545","title":"Addressing Emotion Bias in Music Emotion Recognition and Generation with Frechet Audio Distance","created":"2024-09-23","cited_by_count":0,"area":null},{"id":"2409.17899","title":"Exploring Acoustic Similarity in Emotional Speech and Music via Self-Supervised Representations","created":"2024-09-26","cited_by_count":0,"area":null},{"id":"2410.08321","title":"Music Genre Classification using Large Language Models","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2410.16785","title":"Annotation-Free MIDI-to-Audio Synthesis via Concatenative Synthesis and Generative Refinement","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2411.01661","title":"Sing-On-Your-Beat: Simple Text-Controllable Accompaniment Generations","created":"2024-11-03","cited_by_count":0,"area":null},{"id":"2501.01094","title":"MMVA: Multimodal Matching Based on Valence and Arousal across Images, Music, and Musical Captions","created":"2025-01-02","cited_by_count":0,"area":null}],"next_cursor":"100"}