Dynamically Scaled Activation Steering
- Apple: 89 events in the last 90 days
- Previous: 1 days earlier · REVERSAL-BENCH: A Reversibility Axis and Reset Oracle for Measuring the Reset-Free RL Cliff
What happened
Activation steering has emerged as a powerful method for guiding the behavior of generative models towards desired outcomes such as toxicity…
Summary assembled by rule from the sources below
Why it's spreading
Sources
Official
- Dynamically Scaled Activation SteeringApple Machine Learning