collaborators

9 papers

eess.AS2026

Beyond Reconstruction: Full-Context Generative DiT for Music Generation

Yunjia Li, Menglin Wu, Junyu Dai +13

Hybrid music generators combine the long-range planning of an autoregressive language model with the fidelity of a diffusion- or flow-based acoustic renderer. Yet renderers are tra…

cs.SD2026

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering

Junyu Dai, Xinyue Fan, Weiqin Li +14

In this report, we present a unified song generation framework capable of producing high-quality full-length music from lyrics, text descriptions, and musical attributes. The propo…

cs.SD2026

MMAE: A Massive Multitask Audio Editing Benchmark

Ziyang Ma, Ruiqi Yan, Ruiyang Xu +35

We introduce MMAE, a Massive Multitask Audio Editing benchmark, serving as the first comprehensive evaluation testbed designed for general-purpose instruction-based audio editing.…

cs.SD2026

Resonate: Reinforcing Text-to-Audio Generation via Online Feedback from Large Audio Language Models

Xiquan Li, Junxi Liu, Wenxi Chen +3

Reinforcement Learning (RL) has become an effective paradigm for enhancing Large Language Models (LLMs) and visual generative models. However, its application in text-to-audio (TTA…

cs.SD2025

LeVo: High-Quality Song Generation with Multi-Preference Alignment

Shun Lei, Yaoxun Xu, Zhiwei Lin +10

Recent advances in large language models (LLMs) and audio language models have significantly improved music generation, particularly in lyrics-to-song generation. However, existing…

cs.SD2025

Layer-wise Investigation of Large-Scale Self-Supervised Music Representation Models

Yizhi Zhou, Haina Zhu, Hangting Chen

Recently, pre-trained models for music information retrieval based on self-supervised learning (SSL) are becoming popular, showing success in various downstream tasks. However, the…