SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law
Paper • 2507.18576 • Published • 10
Frank Chen
quantumfr
AI & ML interests
alignment and Interpretability
Recent Activity
upvoted a paper 3 days ago
ATBench: A Diverse and Realistic Trajectory Benchmark for Long-Horizon Agent Safety upvoted a paper 4 days ago
DARE: Diffusion Large Language Models Alignment and Reinforcement ExecutorOrganizations
authored 5
papers 6 months ago
Taming Masked Diffusion Language Models via Consistency Trajectory Reinforcement Learning with Fewer Decoding Step
Paper • 2509.23924 • Published • 9
Rethinking Entropy Regularization in Large Reasoning Models
Paper • 2509.25133 • Published • 4
Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models
Paper • 2509.23962 • Published • 5
Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring
Paper • 2502.05242 • Published