Showing 2026Show all
3 papers · 1 filter
cs.AI2026
Neurosymbolic Alignment for Physiologically-Safe Clinical Language Models
Abdulhady Abas Abdullah, Erik Cambria, Milena Zivkovic
Clinical LLMs can generate recommendations that are factually plausible yet physiologically unsafe. We investigate whether safety alignment can be improved by grounding preference…
cs.AI2026
TUR-DPO: Topology- and Uncertainty-Aware Direct Preference Optimization
Abdulhady Abas Abdullah, Fatemeh Daneshfar, Seyedali Mirjalili +1
Aligning large language models (LLMs) with human preferences is commonly done via reinforcement learning from human feedback (RLHF) with Proximal Policy Optimization (PPO) or, more…
cs.CV2026
BiCLIP: Bidirectional and Consistent Language-Image Processing for Robust Medical Image Segmentation
Saivan Talaei, Fatemeh Daneshfar, Abdulhady Abas Abdullah +1
Medical image segmentation is a cornerstone of computer-assisted diagnosis and treatment planning. While recent multimodal vision-language models have shown promise in enhancing se…