AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

YuE: Scaling Open Foundation Models for Long-Form Music Generation

Ruibin Yuan, Hanfeng Lin, Shuyue Guo, Ge Zhang, Jiahao Pan, Yongyi Zang, Haohe Liu, Yiming Liang, Wenye Ma, Xingjian Du, Xeron Du, Zhen Ye and 46 more

ICLR 2026 · Image generation › Autoregressive and latent generation · approach: Controllable music generation · 101 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Dual-NTP (separate vocal and accompaniment tokens) instead of standard NTP (ablation)YuE 0.5B LM · training loss, 20B tokenstraining loss: approximately 0.4 lower lossImproved
add structural progressive conditioning (CoT) versus vanilla, curriculum, or RoPE base change (ablation)YuE 0.5B LM · lyrics-following WER over 30-150 sWERImproved
scale model from 0.5B to 7B (ablation)YuE · lyrics-following WERWER: approximately 70% -> around 20%Improved
increase RoPE base from 10K to 100K (ABF) or use curriculum on duration (ablation)YuE 0.5B LM · lyrics-following WERWERNo clear effect
add CFG on top of ICL at inference (ablation)YuE-7B · musicality A/B win ratewin rate: 0.63 -> 0.79Improved
use ICL reference audio instead of CoT only at inference (ablation)YuE-7B · musicality A/B win ratewin rate: 0.21 -> 0.63Improved
use semantic-acoustic fused tokenizer (X-Codec) instead of pure acoustic codecs (ablation)YuE LM · LM convergence on in-the-wild musicLM convergenceImproved
introduce ICL data early in pre-training rather than only during annealing (ablation)YuE · pre-training with ICLcreativity / lyric controlHurt
increase TTS data proportion excessively in multitask mix (ablation)YuE · non-rap genressinging qualityHurt
YuE vs CLAP score as automated alignment metric correlated with human lyric followingCLaMP 3 vs CLAP · correlation with LyricFollowPearson correlation: CLaMP 3 0.42 vs CLAP -0.25Mixed
vocal range as proxy metric for musicalityautomatic metrics · correlation with human musicalityPearson correlation: 0.857Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy