by Ryan Li Papers
3 papers found
Automated Hypothesis Validation with Agentic Sequential Falsifications
Kexin Huang, Ying Jin, Ryan Li et al.
ICML 2025poster
BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems
Andy Zhang, Joey Ji, Celeste Menders et al.
NeurIPS 2025posterarXiv:2505.15216
9
citations
OpenCUA: Open Foundations for Computer-Use Agents
Xinyuan Wang, Bowen Wang, Dunjie Lu et al.
NeurIPS 2025spotlight