{"total":68,"rows":[{"id":"2503.23037","title":"Agentic Large Language Models, a survey","created":"2025-03-29","cited_by_count":108,"area":"agents"},{"id":"2405.19327","title":"MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series","created":"2024-05-29","cited_by_count":67,"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":"2404.18081","title":"ComposerX: Multi-Agent Symbolic Music Composition with LLMs","created":"2024-04-28","cited_by_count":42,"area":"agents"},{"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":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37,"area":"diffusion"},{"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":"2404.16969","title":"COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations","created":"2024-04-25","cited_by_count":14,"area":null},{"id":"2407.20962","title":"MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions","created":"2024-07-30","cited_by_count":13,"area":null},{"id":"2410.00872","title":"Do Music Generation Models Encode Music Theory?","created":"2024-10-01","cited_by_count":13,"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":"2410.18336","title":"Assessing the Creativity of LLMs in Proposing Novel Solutions to Mathematical Problems","created":"2024-10-24","cited_by_count":11,"area":null},{"id":"2402.17467","title":"Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey","created":"2024-02-27","cited_by_count":10,"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":"2410.22269","title":"Fourier Head: Helping Large Language Models Learn Complex Probability Distributions","created":"2024-10-29","cited_by_count":10,"area":"offlinerl"},{"id":"2506.05104","title":"Survey on the Evaluation of Generative Models in Music","created":"2025-06-05","cited_by_count":10,"area":null},{"id":"2509.04744","title":"WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning","created":"2025-09-05","cited_by_count":10,"area":"lr"},{"id":"2402.17645","title":"SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition","created":"2024-02-27","cited_by_count":9,"area":null},{"id":"2407.21531","title":"Can LLMs \"Reason\" in Music? An Evaluation of LLMs' Capability of Music Understanding and Generation","created":"2024-07-31","cited_by_count":7,"area":"lr"},{"id":"2410.17218","title":"Creativity in AI: Progresses and Challenges","created":"2024-10-22","cited_by_count":7,"area":null},{"id":"2510.01812","title":"SingMOS-Pro: An Comprehensive Benchmark for Singing Quality Assessment","created":"2025-10-02","cited_by_count":7,"area":null},{"id":"2504.17376","title":"On-Device Qwen2.5: Efficient LLM Inference with Model Compression and Hardware Acceleration","created":"2025-04-24","cited_by_count":6,"area":"inference"},{"id":"2509.04059","title":"Towards an AI Musician: Synthesizing Sheet Music Problems for Musical Reasoning","created":"2025-09-04","cited_by_count":6,"area":"lr"},{"id":"2509.23350","title":"ABC-Eval: Benchmarking Large Language Models on Symbolic Music Understanding and Instruction Following","created":"2025-09-27","cited_by_count":6,"area":null},{"id":"2602.13685","title":"AuTAgent: A Reinforcement Learning Framework for Tool-Augmented Audio Reasoning","created":"2026-02-14","cited_by_count":6,"area":"lr"},{"id":"2409.09601","title":"A Survey of Foundation Models for Music Understanding","created":"2024-09-15","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":"2505.09825","title":"KRISTEVA: Close Reading as a Novel Task for Benchmarking Interpretive Reasoning","created":"2025-05-14","cited_by_count":4,"area":"lr"},{"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":"2505.20638","title":"Music Audio-Visual Question Answering Requires Specialized Multimodal Designs","created":"2025-05-27","cited_by_count":4,"area":"mllm"},{"id":"2506.23009","title":"MusiXQA: Advancing Visual Music Understanding in Multimodal Large Language Models","created":"2025-06-28","cited_by_count":4,"area":"lr"},{"id":"2505.19294","title":"Towards Reliable Large Audio Language Model","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2508.01394","title":"Via Score to Performance: Efficient Human-Controllable Long Song Generation with Bar-Level Symbolic Notation","created":"2025-08-02","cited_by_count":3,"area":null},{"id":"2604.03333","title":"Composer Vector: Style-steering Symbolic Music Generation in a Latent Space","created":"2026-04-03","cited_by_count":3,"area":null},{"id":"2604.19532","title":"BEAT: Tokenizing and Generating Symbolic Music by Uniform Temporal Steps","created":"2026-04-21","cited_by_count":3,"area":null},{"id":"2506.18783","title":"TRIZ Agents: A Multi-Agent LLM Approach for TRIZ-Based Innovation","created":"2025-06-23","cited_by_count":2,"area":"agents"},{"id":"2506.23128","title":"Are Large Language Models Capable of Deep Relational Reasoning? Insights from DeepSeek-R1 and Benchmark Comparisons","created":"2025-06-29","cited_by_count":2,"area":"lr"},{"id":"2601.11556","title":"CSyMR: Benchmarking Compositional Music Information Retrieval in Symbolic Music Reasoning","created":"2025-12-16","cited_by_count":2,"area":"lr"},{"id":"2602.03023","title":"Rethinking Music Captioning with Music Metadata LLMs","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2407.10328","title":"The Interpretation Gap in Text-to-Music Generation Models","created":"2024-07-14","cited_by_count":1,"area":null},{"id":"2410.22299","title":"Emotion-Guided Image to Music Generation","created":"2024-10-29","cited_by_count":1,"area":null},{"id":"2507.02282","title":"Content filtering methods for music recommendation: A review","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2509.00132","title":"CoComposer: LLM Multi-agent Collaborative Music Composition","created":"2025-08-29","cited_by_count":1,"area":"agents"},{"id":"2511.03942","title":"MIDI-LLM: Improving Text-to-MIDI Music Generation via Adapting Large Language Models","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2511.12077","title":"Learning to Hear by Seeing: It's Time for Vision Language Models to Understand Artistic Emotion from Sight and Sound","created":"2025-11-15","cited_by_count":1,"area":"mllm"},{"id":"2511.16478","title":"Music Recommendation with Large Language Models: Challenges, Opportunities, and Evaluation","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2601.22764","title":"How Far Can Pretrained LLMs Go in Symbolic Music? Controlled Comparisons of Supervised and Preference-based Adaptation","created":"2026-01-30","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":"2606.12555","title":"AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation","created":"2026-06-10","cited_by_count":1,"area":"diffusion"},{"id":"2609.16034","title":"StepAudio 3 Music Technical Report","created":"2026-09-11","cited_by_count":1,"area":"diffusion"},{"id":"2409.05521","title":"Harmonic Reasoning in Large Language Models","created":"2024-09-09","cited_by_count":0,"area":"lr"},{"id":"2412.06617","title":"AI TrackMate: Finally, Someone Who Will Give Your Music More Than Just \"Sounds Great!\"","created":"2024-12-09","cited_by_count":0,"area":null},{"id":"2506.23094","title":"TOMI: Transforming and Organizing Music Ideas for Multi-Track Compositions with Full-Song Structure","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2507.04776","title":"Improving BERT for Symbolic Music Understanding Using Token Denoising and Pianoroll Prediction","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2507.23334","title":"MUST-RAG: MUSical Text Question Answering with Retrieval Augmented Generation","created":"2025-07-31","cited_by_count":0,"area":"rag"},{"id":"2509.04899","title":"Encoding of musical structures in hidden units of restricted Boltzmann machines","created":"2025-09-05","cited_by_count":0,"area":null},{"id":"2509.25694","title":"HNote: Extending YNote with Hexadecimal Encoding for Fine-Tuning LLMs in Music Modeling","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2512.05430","title":"ArtistMus: A Globally Diverse, Artist-Centric Benchmark for Retrieval-Augmented Music Question Answering","created":"2025-12-05","cited_by_count":0,"area":"rag"},{"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":"2604.20719","title":"ONOTE: Hypergraph-Grounded Omnimodal Reasoning for Computational Music Science","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2606.08722","title":"Can LLMs understand LilyPond? A benchmark for symbolic music generation and understanding","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.22708","title":"Libretto: Giving LLM Agents a Sense of Musical Structure","created":"2026-06-21","cited_by_count":0,"area":"agents"},{"id":"2608.03032","title":"DDSynth-RL: Audio Synthesizer Inversion via Discrete Diffusion with Reinforcement Learning","created":"2026-08-04","cited_by_count":0,"area":"diffusion"},{"id":"2609.13291","title":"ScorePrompts: Natural-Language Exploration of Symbolic Music Scores through Analysis","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.22150","title":"ECP-Bench: Benchmarking and Learning Entertainment Content Promotion with Foundation Models","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.23665","title":"Which Constraints Are Missing? Ask the Verifier: Graded Rewards for Constraint-Following Music Generation","created":"2026-09-20","cited_by_count":0,"area":"alignment"},{"id":"2610.15957","title":"Harmonic Representations in Symbolic Music Transformers are Localized and Controllable","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}