GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification
Paper • 2604.14258 • Published • 23
Wangjie Gan
zju-omniai
·
AI & ML interests
None yet
Recent Activity
authored a paper 3 days ago
GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification commentedon a paper 3 days ago
GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient RectificationOrganizations
authored a
paper 3 days ago