2 papers
stat.ML2025
Minimax Rates for Learning Pairwise Interactions in Attention-Style Models
Shai Zucker, Xiong Wang, Fei Lu +1
We study the convergence rate of learning pairwise interactions in single-layer attention-style models, where tokens interact through a weight matrix and a nonlinear activation fun…
cs.CV2025
A Geometric Unification of Generative AI with Manifold-Probabilistic Projection Models
Leah Bar, Liron Mor Yosef, Shai Zucker +3
Most models of generative AI for images assume that images are inherently low-dimensional objects embedded within a high-dimensional space. Additionally, it is often implicitly ass…