Zhaoyang Liu

Privilege-induced style drift can undermine reasoning model performance, but RLCSD effectively redirects the learning signal to focus on what truly matters—task-relevant tokens.

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

Forget prompt engineering: E2E-REME directly generates executable Ansible playbooks from diagnosis reports, outperforming large LLMs in microservice auto-remediation accuracy and efficiency.

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.