Unifying Symbolic and Audio Music Generation at Frontier Quality. Rivals Suno v5; covers & agentic editing. MERT2, SheetSage2, VAEs, WildSongBench.
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
SheetSage2: Coherent Lead-Sheet Transcription with Synthetic Supervision
YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality
Organization Card
Multimodal Art Projection (M-A-P) is an open-source AI research community.
The community members are working on research topics in a wide range of spectrum, including but not limited to pre-training paradigm of foundation models, large-scale data collection and processing, and the derived applciations on coding, reasoning and music creativity.
The community is open to researchers keen on any relevant topic. Welcome to join us!
- Discord Channel
- Our Full Paper List
- mail: contact@m-a-p.ai
The development log of our Multimodal Art Projection (m-a-p) model family:
- 🔥10/09/2026: We release YuE2, an open-source frontier music generation model that rivals Suno v5, with support for cover song generation and agentic editing. Explore the models and benchmark and listen to the demos.
- 🔥28/01/2025: We release YuE (乐), the most powerful open-source foundation models for music generation, specifically for transforming lyrics into full songs (lyrics2song), like Suno.ai. See demos.
- 🔥08/05/2024: We release the fully transparent large language model MAP-Neo, series models for scaling law exploraltion and post-training alignment, and along with the training corpus Matrix.
- 🔥11/04/2024: MuPT paper and demo are out. HF collection.
- 🔥08/04/2024: Chinese Tiny LLM is out. HF collection.
- 🔥28/02/2024: The release of ChatMusician's demo, code, model, data, and benchmark. 😆
- 🔥23/02/2024: The release of OpenCodeInterpreter, beats GPT-4 code interpreter on HumanEval.
- 23/01/2024: we release CMMMU for better Chinese LMMs' Evaluation.
- 13/01/2024: we release a series of Music Pretrained Transformer (MuPT) checkpoints, with size up to 1.3B and 8192 context length. Our models are LLAMA2-based, pre-trained on world's largest 10B tokens symbolic music dataset (ABC notation format). We currently support Megatron-LM format and will release huggingface checkpoints soon.
- 02/06/2023: officially release the MERT pre-print paper and training codes.
- 17/03/2023: we release two advanced music understanding models, MERT-v1-95M and MERT-v1-330M , trained with new paradigm and dataset. They outperform the previous models and can better generalize to more tasks.
- 14/03/2023: we retrained the MERT-v0 model with open-source-only music dataset MERT-v0-public
- 29/12/2022: a music understanding model MERT-v0 trained with MLM paradigm, which performs better at downstream tasks.
- 29/10/2022: a pre-trained MIR model music2vec trained with BYOL paradigm.
models 218
m-a-p/SheetSage2
Feature Extraction • 57.2M • Updated • 16.4k • 190
m-a-p/YuE2-3B
Text-to-Audio • 4B • Updated • 21.1k • 1.26k
m-a-p/MERT-v2-FullSong
Feature Extraction • 0.6B • Updated • 13.4k • 58
m-a-p/MERT-v2-30s
Feature Extraction • 0.6B • Updated • 925 • 23
m-a-p/YuE2-Vae-legacy
Feature Extraction • 0.1B • Updated • 810 • 12
m-a-p/YuE2-Vae
Feature Extraction • 0.1B • Updated • 19.8k • 41
m-a-p/OProver-8B
Text Generation • 8B • Updated • 704 • 2
m-a-p/OProver-32B
Text Generation • 33B • Updated • 100 • 5
m-a-p/OProver-32B-Round1
Text Generation • 33B • Updated • 11
m-a-p/OProver-8B-Round2
Text Generation • 8B • Updated • 18
datasets 78
m-a-p/06231df73c012a3f0a3e385f76310520
Updated • 6.78k
m-a-p/WildSongBench
Viewer • Updated • 192 • 1.44k • 18
m-a-p/LPFQA
Viewer • Updated • 430 • 243 • 7
m-a-p/TerminalTraj-5k-instances
Updated • 256 • 6
m-a-p/MSQA
Updated • 159 • 2
m-a-p/bins
Updated • 32
m-a-p/ClinPath
Updated • 8
m-a-p/OProofs
Viewer • Updated • 6.8M • 6.81k • 5
m-a-p/PIN-200M
Viewer • Updated • 68.1k • 78.4k • 34
m-a-p/TerminalTraj
Viewer • Updated • 20k • 497 • 12