Han-Qing Zhao

Reimagining computational quantum research with AI scientists

AI scientists are expanding automated research across scientific domains, yet their ability to turn the scientific record into a foundation for autonomous discovery remains elusive. Here we uncover a fundamental barrier to this transition and demonstrate a route to overcome it in computational quantum science, where ad...

This paper is included in the Proceedings of the 35th USENIX Security Symposium.

Escaping Confidence Trap: Evolutionary Decoding for Mathematical Reasoning in Diffusion LLMs

This work analyzes the decoding trajectories of LLaDA 2.0 and identifies a recurring diffusion confidence trap, which improves LLaDA 2.0 over confidence-based decoding, leading to more reliable mathematical reasoning.

Breadcrumbing Search Agents

This work studies the channel delivering search and page observations is a fragile security boundary and introduces Authority-Chain Hijack (ACH), an expert-refined strategy that turns isolated search-result and page-content manipulations into a coherent evidence chain across seemingly corroborating sources.