Hugging Face Papers ↗ · 2026-11-19
RL Post-Training in Diffusion Transformers Is Activation Steering
Media reports Hugging Face Papers Source language: Chinese
A fixed set of steering vectors added to a frozen diffusion transformer recovers most quality gains from reinforcement learning post-training. This indicates that improvements stem largely from a constant shift rather than prompt-specific transformations.
Full text
A fixed set of steering vectors added to a frozen diffusion transformer recovers most of the quality gains from reinforcement learning post-training, indicating that much of the improvement comes from a constant shift rather than prompt-specific transformations.