Dongrui Liu
shenqiorient
AI & ML interests
Trustworthy AI
Recent Activity
upvoted a paper about 2 months ago
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability upvoted a paper about 2 months ago
ATBench: A Diverse and Realistic Trajectory Benchmark for Long-Horizon Agent Safety