Xiangyang Zhou

发表论文 5 篇 · 总被引 41 次 · h-index 2

代表论文

• The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions (2025 · International Conference on Machine Learning · 被引 33)
• The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Safety Analysis (2025 · arXiv.org · 被引 18)
• M*: Every Task Deserves Its Own Memory Harness (2026 · arXiv.org · 被引 6)
• Upholding academic integrity: an exploratory study of AI-assisted detection of unauthorised machine translation use in student translations (2026 · Humanities and Social Sciences Communications · 被引 1)
• Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference (2026 · arXiv.org · 被引 1)