الباحثون

Xin He

المنشورات 2

نسخة أولية وصول مفتوح

Origins of Universal Machine Learning Force-Field Errors in Multicomponent Materials

Hongwei Du, Dingyang Lv, Baole Wei وآخرون · 2026

Universal machine learning force-field generalization to multicomponent environments generated by compositional design remains insufficiently assessed. We construct a benchmark of 7,599 multicomponent configurations inspired by high-entropy design, elemental substitution and anion mixing. Eleven pretrained models are e …

نسخة أولية وصول مفتوح

SkillPoison: Progressive Skill Poisoning via Successful Experiences

Lizhi Zhang, Xin He, Dianxuan Fu وآخرون · 2026

Self-improving LLM agents increasingly distill successful experiences into persistent, reusable skills. Existing skill attack methods corrupt this learning pipeline by injecting malicious triggers, behaviors, or false facts into individual experiences or extracted skills. However, such attacks are easily detected, and …

المؤلفون المشاركون