2 papers
cs.CV2026
UHP Detection: LVLMs have their Unique Hallucination Pattern in the Consistency Space
Amir Mohammad Ezzati, Kiyan Rezaee, Bardiya Kariminia +4
Large vision--language models (LVLMs) demonstrate strong multimodal reasoning capabilities but remain prone to hallucination, where model predictions are not grounded in visual evi…
cs.CV2025
All Centers Are at most a Few Tokens Apart: Knowledge Distillation with Domain Invariant Prompt Tuning
Amir Mohammad Ezzati, Alireza Malekhosseini, Armin Khosravi +1
Domain generalization is critical in computational pathology (CPath) due to inherent domain shifts caused by variations in staining protocols, scanner devices, and imaging settings…