{"total":16,"rows":[{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2308.05037","title":"Separate Anything You Describe","created":"2023-08-09","cited_by_count":43,"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":"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},{"id":"2409.07827","title":"Bridging Paintings and Music -- Exploring Emotion based Music Generation through Paintings","created":"2024-09-12","cited_by_count":6,"area":null},{"id":"2507.09834","title":"Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction","created":"2025-07-14","cited_by_count":5,"area":null},{"id":"2406.00294","title":"Creative Text-to-Audio Generation via Synthesizer Programming","created":"2024-06-01","cited_by_count":4,"area":null},{"id":"2412.15922","title":"RiTTA: Modeling Event Relations in Text-to-Audio Generation","created":"2024-12-20","cited_by_count":3,"area":null},{"id":"2508.20088","title":"AudioStory: Generating Long-Form Narrative Audio with Large Language Models","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2602.01634","title":"HuPER: A Human-Inspired Framework for Phonetic Perception","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2401.07532","title":"Multi-view MidiVAE: Fusing Track- and Bar-view Representations for Long Multi-track Symbolic Music Generation","created":"2024-01-15","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":"2510.00485","title":"PodEval: A Multimodal Evaluation Framework for Podcast Audio Generation","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2509.15253","title":"Emotion-Aware Speech Generation with Character-Specific Voices for Comics","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2509.15986","title":"EmoHeal: An End-to-End System for Personalized Therapeutic Music Retrieval from Fine-grained Emotions","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2602.10964","title":"Can LLMs Cook Jamaican Couscous? A Study of Cultural Novelty in Recipe Generation","created":"2026-02-11","cited_by_count":0,"area":null}],"next_cursor":null}