3 papers
cs.CV2025
Spatially Grounded Concept-Based Image Classification
Ran Eisenberg, Amit Rozner, Ethan Fetaya +1
Deep neural networks can achieve high accuracy while relying on evidence that is hard to inspect or misaligned with the intended task. Concept Bottleneck Models (CBMs) expose human…
cs.CL2024
Knowledge Editing in Language Models via Adapted Direct Preference Optimization
Amit Rozner, Barak Battash, Lior Wolf +1
Large Language Models (LLMs) can become outdated over time as they may lack updated world knowledge, leading to factual knowledge errors and gaps. Knowledge Editing (KE) aims to ov…
cs.CV2024
Obtaining Favorable Layouts for Multiple Object Generation
Barak Battash, Amit Rozner, Lior Wolf +1
Large-scale text-to-image models that can generate high-quality and diverse images based on textual prompts have shown remarkable success. These models aim ultimately to create com…