Author

Zeming Wei

Peking University

h-index 13 Homepage View on Semantic Scholar

We have 3 of 36 papers

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.

Preprint Sep 2026

LexiconVLA: Learning Reusable Atomic Action Codebooks for Unseen Tasks

Vision-language-action (VLA) models struggle to reuse recurring interactions in unseen tasks. Our diagnostic study reveals that reliable task completion does not imply consistent execution of constituent atomic actions across task contexts. We present LexiconVLA, a retrievable atomic-action lexicon for cross-task reuse...

Zeming Wei, Jian-Heng Ye, Xin-Shuai Song et al. · 0 citations

#artificial intelligence May 2026

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces

This work presents SkillSafetyBench, a runnable benchmark for evaluating skill-facing safety failures, and suggests that agent safety depends not only on model-level alignment, but also on how agents interpret skills, trust workflow context, and act through executable environments.

Chang Jin, Anr'an W'ang, Zeming Wei et al. · arXiv.org · 11 citations · ⚡1

Replay-free Sequential Fine-tuning of Medical VLMs

The streamlined, replay-free approach proves highly effective on a new continual learning benchmark and a practical path toward building prehensive, continually-learning medical VLMs and advancing the development of medical AI.

Hefei Li, Yuhui Zhang, Xiaohan Wang et al. · 0 citations