Apple Workshop on Machine Learning for Health: Towards Increasing Diversity in Mobile Sensing Research
AuthorsDaniel Gatica-Perez (IDIAP-EPFL)
Apple Workshop on Machine Learning for Health: Towards Increasing Diversity in Mobile Sensing Research
AuthorsDaniel Gatica-Perez (IDIAP-EPFL)
How to Guide Your Language Flow
September 23, 2026research area Methods and Algorithms
We introduce a new method to guide flow matching models. Our approach, which we call probe guidance, uses the frozen internal states of an existing diffusion model to construct a guidance signal. This works using a similar principle as autoguidance, but eliminates the need for an additional forward pass at inference time and provides a reliable path to ensure that the weak and strong model share similar dynamics. We apply and benchmark this…
Dynamically Scaled Activation Steering
September 18, 2026research area Human-Computer Interaction, research area Methods and AlgorithmsTransactions on Machine Learning Research (TMLR)
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 introduce Dynamically Scaled Activation Steering (DSAS), a method-agnostic steering framework that decouples when to steer from how to steer. DSAS…