arxiv:2606.05080
Zhangchen Xu PRO
zhangchenxu
AI & ML interests
LLM Data, Alignment, Post-Training, Safety
Recent Activity
authored a paper 5 days ago
SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge authored a paper 5 days ago
Building a Foundational Guardrail for General Agentic Systems via
Synthetic Data authored a paper 5 days ago
PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic MemoryOrganizations
arxiv:2605.12684
arxiv:2603.27771
arxiv:2512.06688
arxiv:2510.09781
arxiv:2510.01179
arxiv:2509.19212
arxiv:2505.23977
arxiv:2505.21605
arxiv:2505.14625
arxiv:2503.02951
arxiv:2502.12143
arxiv:2502.12025
arxiv:2411.07133
arxiv:2406.12257
arxiv:2406.12935
arxiv:2406.08464
arxiv:2402.11753
arxiv:2402.08983
