Joint Scaling
A strategy in DMD distillation that scales the critic in tandem with the teacher model to maintain capacity matching, preventing training collapse and improving distillation effectiveness.
Timeline (last 90 days)
A joint scaling strategy that scales the critic in tandem with the teacher prevents training collapse and enables the student model to benefit from a larger teacher.
Combined with joint scaling, STAC yields consistent improvements on class-conditional ImageNet generation.
Combined with joint scaling, STAC confirms the effectiveness of the method on Wan2.1-based text-to-video generation.
All Facts (3)
A joint scaling strategy that scales the critic in tandem with the teacher prevents training collapse and enables the student model to benefit from a larger teacher.
50%UnverifiedCombined with joint scaling, STAC yields consistent improvements on class-conditional ImageNet generation.
50%UnverifiedCombined with joint scaling, STAC confirms the effectiveness of the method on Wan2.1-based text-to-video generation.
50%