Junwei Liao's repositories
Constitutional-AI
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
Language:PythonApache-2.0000
data-driven_model_for_student_financial_aid_allocation
This is a paper participating in the school-level mathematical modeling competition
Language:TeX000
FeDPO
Implementation for FeDPO (Federated Direct Preference Optimization)
Language:Python000
jwliao-ai.github.io
Junwei Liao's homepage.
Language:HTML000