Author

Changxuan Fan

Observed name: Fan, Changxuan

Institutions: University of Science and Technology, Hong Kong University of Science and Technology, New York University, Korea University of Science and Technology

Observed institutions: University of Science and Technology, Hong Kong University of Science and Technology, New York University, Korea University of Science and Technology

OpenAlex ID: A5140851519

SkillScriptBench: Benchmarking Self-Evolution of Executable Agent Skill Packages Beyond Markdown

2026 · Liu, Yuxuan, Li, Haoran, et al. · arXiv (Cornell University) · 2

OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance Dataset

2026 · Hu, Wenbin, Jing, Huihao, et al. · arXiv (Cornell University) · 2

RLPF: Reinforcement Learning from Performance Feedback for Code Generation

2026 · Jing, Huihao, Cui, Haozhe, et al. · arXiv (Cornell University) · 1

Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries

2026 · Hung, Ki Sen, Yang, Xi, et al. · arXiv (Cornell University) · 1

Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries

2026 · Association for Computational Linguistics 2026, Chen, Kejiang, et al. · Underline Science Inc.

OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance Dataset

2026 · Association for Computational Linguistics 2026, Fan, Changxuan, et al. · Underline Science Inc.

Works count: 6

Citation count: 6

H-index: 2

I10-index: