← authors · overview

• MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training
  2023 · 27 citations
• ChatMusician: Understanding and Generating Music Intrinsically with LLM
  2024 · 4 citations
• LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT
  2023 · 3 citations
• MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learning
  2022 · 2 citations
• On the Effectiveness of Speech Self-supervised Learning for Music
  2023 · 2 citations
• YuE: Scaling Open Foundation Models for Long-Form Music Generation
  2025
• CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following
  2025
• Learnable Front Ends Based on Temporal Modulation for Music Tagging
  2022
• MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series
  2024
• OmniBench: Towards The Future of Universal Omni-Language Models
  2024