2 papers
cs.CL2025
SAFER: Advancing Safety Alignment via Efficient Ex-Ante Reasoning
Kehua Feng, Keyan Ding, Yuhao Wang +5
Recent advancements in large language models (LLMs) have accelerated progress toward artificial general intelligence, yet their potential to generate harmful content poses critical…
cs.AI2025
Enhancing Safe and Controllable Protein Generation via Knowledge Preference Optimization
Yuhao Wang, Keyan Ding, Kehua Feng +5
Protein language models have emerged as powerful tools for sequence generation, offering substantial advantages in functional optimization and denovo design. However, these models…