2 papers
cs.CV2026
RRFC: Recursive Refinement via Feedback Conditioning for Iterative Image-to-Image Generation
Kareem Hassani, Chaymaa Abbas, Hadi Al Mubasher +1
Conditional image-to-image generators are single-shot: they map input features to an output in one forward pass and treat it as final, with no opportunity to improve on it. Althoug…
cs.AI2026
THESIS-MoE: Trainable Hierarchical Extraction and SteerIng of Sycophancy in Mixture-of-Experts
Kareem Hassani, Chaymaa Abbas, Lama Mawlawi +1
Sycophancy, the tendency of a language model to change its answer to match a user's stated belief, is a common alignment failure. Existing activation steering methods typically app…