FLIP: Final Layer Inference-Time Probing for Vision-Language Models
We present FLIP, a final-layer inference-time probe for testing whether a logit-facing intervention site in an open-weight vision-language model (VLM) supports structured, task-linked computation rather than generic perturbation. Behavioral change under internal intervention is otherwise mechanistically ambiguous: it m...
Drandreb Earl O. Juanico, Rowel O. Atienza
· 0 citations