arXiv CS AI
techCenter
Probing Perceptual Priors of MLLMs via Gibbs Sampling with Interpretable Generative Controlstranslating…
arXiv:2608.27727v1 Announce Type: new
Abstract: A model's behavior on a task is jointly determined by the input it receives and the prior it brings in, i.e. the distribution over stimuli it implicitly expects. Interpretability research has traditionally studied models by…
Keywords#Controls#Generative#Generative Controls#Gibbs#Gibbs Sampling