Dongrui Liu
shenqiorient
AI & ML interests
Trustworthy AI
Recent Activity
upvoted a paper about 10 hours ago
ATBench: A Diverse and Realistic Trajectory Benchmark for Long-Horizon Agent Safety upvoted a paper 23 days ago
OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data upvoted a paper about 1 month ago
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training
and DeploymentOrganizations
