2 papers
cs.CV2026
Don't Just Look, Intervene: Perturbation Based Region Labeling for VQA Images
Marko Jojic, Zhaonan Li, Ben Zhou
Vision Language Models (VLMs) should rely on visual evidence that directly determines the correct answer, but supervision for grounding visual reasoning is often expensive to obtai…
cs.AI2025
GenZ: Foundational models as latent variable generators within traditional statistical models
Marko Jojic, Nebojsa Jojic
We present GenZ, a hybrid model that bridges foundational models and statistical modeling through interpretable semantic features. While large language models possess broad domain…