Yilin Zhao

Language, when self-evolving and treated as a physical representation, can unlock state-of-the-art physical plausibility in video world models, even surpassing proprietary systems.

Co-Scientist not only accelerates scientific discovery but also ensures the reliability of generated research outputs, reducing hallucination and plagiarism in a double-blind study.

The latest AI City Challenge reveals that integrating foundation models with synthetic data design can significantly boost performance in complex urban scenarios.

WIFA reduces harmful refusal while minimizing benign over-refusal, achieving a remarkable drop in over-refusal rates from 25.7% to 17.4%.

Mainstream LLMs struggle to navigate safety risks in scientific applications, revealing critical vulnerabilities in AI4Science workflows.