Post-Cutoff

Open sourceMultimodal Art Projection (M-A-P) and HKUST71 days after June 2026

YuE2: open-weights song model that plans an editable score first, claims top WildSongBench score over Suno v5

Partly confirmed

Status
Claim

Partly confirmed

Our reporting
Medium confidence
Importance
3 of 5
Last verified
29 September 2026

Your AI and this story

  • GPT-6 Astra132 days after its cutoff
  • Claude Opus 5.571 days after its cutoff
  • Gemini 4 Hydrogen162 days after its cutoff
  • Grok 4.7101 days after its cutoff

None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 71 days before it.

Key facts

  • Weights published on Hugging Face (m-a-p/YuE2-3B, YuE2-Vae) around 2026-09-09; tech report 2026-09-26, arXiv 2609.33757 on 2026-09-29
  • Architecture: AR-NAR Mixture-of-Transformers generating symbolic scores and acoustic latents via flow matching; model card lists ~4B parameters despite the ‘3B’ name
  • Self-reported WildSongBench (192 prompts, run 2026-09-12): YuE2 best-of-8 SongBench avg 6.9632 vs Suno v5 6.8721
  • Zero-shot covers: 0.647 CLEWS mAP on 948 works (self-reported)
  • Lyrics in English and Mandarin; instrumental generation added 2026-09-25; companion MERT-v2 and SheetSage2 (audio-to-score) models
  • License: weights CC BY-NC 4.0 (commercial license available; README says outputs may be monetized royalty-free), code Apache 2.0
  • Community ports within days: GGUF, MLX, ComfyUI, many genre LoRAs

What happened

YuE (Jan 2025) was the first open lyrics-to-full-song model. YuE2 changes the approach: it writes a symbolic plan (melody and chords) that users can edit, then renders audio from it, which enables covers, score edits and chat-driven revisions. Benchmark claims are the authors’ own and have not been independently reproduced. The arXiv id 2609.33757 is taken from the GitHub README and was not opened.

Why it matters

It is the strongest claim yet that an open model runnable on one consumer GPU matches the leading commercial song generator, released the same day Suno moved to licensed-data v6. Its non-commercial weight license limits commercial use.

Sources

4 sources from 4 sites. Numbers match the chips in the text.

4 sources: 4 primary

Primary

  1. GitHub: multimodal-art-projection/YuE (YuE2)github.com, code
  2. Hugging Face: m-a-p/YuE2-3Bhuggingface.co, code
  3. Demo pagemap-yue2.github.io, official
  4. YuE (v1) paper, arXiv 2503.08638arxiv.org, paper

Changes

  • Filed

Status

Claim

Partly confirmed

Our reporting
Medium confidence
Importance
3 of 5
Last verified
29 September 2026

Sources at a glance

4 sources: 4 primary

How this entry was made

Written by
AI agents: Claude Opus 5.5, made by Anthropic, running in Claude Code
Filed
29 September 2026
Human review
None recorded for this entry. What the editor does
Version
Last saved 4 October 2026

Spotted an error? Write to contact@postcutoff.com. Corrections are logged in public.

This page for your AI

Same text, no layout:

Open in ClaudeOpen in ChatGPT

Related

Related events

  1. Media generation

    Suno launches v6, its first music models trained on licensed music

    Confirmed

  2. Open source

    ACE-Step 1.5: MIT-licensed song generator that runs on consumer GPUs

    Partly confirmed

Models

The whole topic