Showing 2026Show all
3 papers · 1 filter
cs.CV2026
Enhancing Single-Image Facial Demorphing using Multimodal Large Language Models
Nitish Shukla, Arun Ross
Face recognition systems are increasingly vulnerable to morphing attacks, where a composite image is crafted to match multiple identities, enabling unauthorized access and identity…
cs.CV2026
S2H-DPO: Hardness-Aware Preference Optimization for Vision-Language Models
Nitish Shukla, Surgan Jandial, Arun Ross
Vision-Language Models (VLMs) have demonstrated remarkable progress in single-image understanding, yet effective reasoning across multiple images remains challenging. We identify a…
math.DG2026
On pluricanonical locally conformally almost Kähler metrics
Ethan Addison, Tedi Draghici, Mehdi Lejmi
On an almost complex manifold , a pluricanonical locally conformally almost Kähler (LCAK) metric is induced by a locally conformally symplectic structure of the…