Author

Shao-Heng Yan

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence May 2026

FlashMol: High-Quality Molecule Generation in as Few as Four Steps

This work presents FlashMol, an ultra-fast molecule generative model producing high-quality molecular conformations in as few as 4 steps, and adapt distribution matching distillation (DMD) -- a reverse KL-divergence minimization objective -- to the molecular domain for effective distillation.

Xinyuan Wei, Zian Li, Shao-Heng Yan et al. · arXiv.org · 1 citation

#artificial intelligence Preprint Oct 2026

DANGERLENS: Probing Dangerous Representations Hidden by Safety Alignment

DANGERLENS is introduced, a probe that maps hidden states into vocabulary space and uses blinded semantic judgments to distinguish harmful goals and operational means from hazard recognition and safety control and introduces a direct audit of intermediate representations.

Tian-Zhuo Yang, Shao-Heng Yan, Lin Lu et al. · 0 citations