REGER adds inter-item relations to generative recommendation with semantic IDs
The method pretrains by generating semantic neighbors' IDs and distills a teacher's full next-token distributions along the target path.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #preference-distillation
Smaller Models, Better Rejects: Preference Distillation Scaling
Smaller frozen models produce more useful preference-distillation rejects than a student's own failures on code and math.