Modulated Intervention Preference Optimization (MIPO): Keep the Easy, Refine the Difficult
Paper • 2409.17545 • Published • 20 •
5
Cheolhun Jang
fetong
AI & ML interests
None yet
Recent Activity
upvoted a paper 4 days ago
On-Policy Delta Distillation upvoted a paper 5 months ago
Weak-Driven Learning: How Weak Agents make Strong Agents Stronger upvoted a paper 8 months ago
TiDAR: Think in Diffusion, Talk in AutoregressionOrganizations
None yet