Rui-Bin Yuan

Key contribution not extracted.

This work introduces StepAudio 3 Music, a large-scale, long-form music generation model that supports explicit musical planning and open-domain text-controlled generation, and achieves the highest AudioBox Content Enjoyment, Content Usefulness, and Production Quality scores and the highest MuQ-MuLan similarity among the evaluated systems.

As human oversight wanes, LRMs could autonomously evolve, but this shift introduces significant risks like reward hacking and feedback drift.

Automated data curation and imbalance-aware training strategies significantly enhance LALMs' performance on culturally diverse folk music, yet deep musical understanding remains elusive.

Embedding reference tokens at semantic positions allows for unprecedented precision in multi-reference video editing, setting a new benchmark for instruction quality.

Achieving a 76.2% relative gain in multi-step reasoning success rates, HDR redefines the capabilities of video models in real-time applications.

Qwen-Music outperforms leading systems in musicality and audio quality, achieving state-of-the-art results across 13 of 16 metrics while generating songs from text and reinterpreting existing tracks.

Achieving high-fidelity audio generation with just four sampling steps, AudioX-Turbo dramatically cuts inference costs while enhancing performance across multimodal tasks.

TACO reduces token overhead by 10% while boosting terminal agent performance by up to 4%, revolutionizing how we approach long-horizon reasoning tasks.

Audio-Omni can edit sound, music, and speech with a single model, rivaling specialized systems and unlocking capabilities like knowledge-augmented reasoning and zero-shot cross-lingual control.