AI RESEARCH

Bodhi VLM: Privacy-Alignment Modeling for Hierarchical Visual Representations in Vision Backbones and VLM Encoders via Bottom-Up and Top-Down Feature Search

arXiv CS.CV

ArXi:2603.13728v1 Announce Type: new Learning systems that preserve privacy often inject noise into hierarchical visual representations; a central challenge is to \emph{model} how such perturbations align with a declared privacy budget in a way that is interpretable and applicable across vision backbones and vision--language models (VLMs