Dynamically Scaled Activation Steering
This story is from 2026-09-18. It is preserved in the archive; the latest stories are on the live feed.
Activation steering has emerged as a powerful method for guiding the behavior of generative models towards desired outcomes such as toxicity mitigation. However, most existing methods apply interventions uniformly across all inputs, degrading model performance when steering is unnecessary. We intro…
Read the full story at Apple Machine Learning Research ↗
Timeline · 1 report
- 2026-09-18 00:00 · Apple Machine Learning Research
Dynamically Scaled Activation Steering