Manuel Cherep

Probing Perceptual Priors of MLLMs via Gibbs Sampling with Interpretable Generative Controls

This work proposes a method to sample from models'perceptual prior distributions directly, by steering a generative model to produce stimuli along controllable axes and running Gibbs sampling over that space with the model under study as the judge, and recovers both canonical biases and surprising novel priors invisible to direct prompting.