🧑🔬 Cheng Wang — papers of 2026 — 2 papers, the most cited first2 papers · all years of Cheng WangFalse Sense of Security: Why Probing-based Malicious Input Detection Fails to GeneralizeFindings of the Association for Computational LinguisticsCheng Wang, Zeming Wei, Qin Liu, et al.2026 · 5 citationsTaming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage ReweightingAnnual Meeting of the Association for Computational Linguistics (ACL)Cheng Wang, Qin Liu, Wenxuan Zhou, et al.2026This page in Markdown → https://md.research.elamur.ai/free/en/authors/cheng-wang/year/2026/