3 papers
cs.CV2026
SPARC: Concept-Aligned Sparse Autoencoders for Cross-Model and Cross-Modal Interpretability
Ali Nasiri-Sarvi, Hassan Rivaz, Mahdi S. Hosseini
Understanding how different AI models encode the same high-level concepts, such as objects or attributes, remains challenging because each model typically produces its own isolated…
cs.CV2026
MonoLoss: A Training Objective for Interpretable Monosemantic Representations
Ali Nasiri-Sarvi, Anh Tien Nguyen, Hassan Rivaz +2
Sparse autoencoders (SAEs) decompose polysemantic neural representations, where neurons respond to multiple unrelated concepts, into monosemantic features that capture single, inte…
cs.CV2025
Ultrasound Image Generation using Latent Diffusion Models
Benoit Freiche, Anthony El-Khoury, Ali Nasiri-Sarvi +5
Diffusion models for image generation have been a subject of increasing interest due to their ability to generate diverse, high-quality images. Image generation has immense potenti…