3 papers
cs.LG2026
Decomposing multimodal embedding spaces with group-sparse autoencoders
Chiraag Kaushik, Davis Barch, Andrea Fanelli
The Linear Representation Hypothesis asserts that the embeddings learned by neural networks can be understood as linear combinations of features corresponding to high-level concept…
stat.ML2025
A general technique for approximating high-dimensional empirical kernel matrices
Chiraag Kaushik, Justin Romberg, Vidya Muthukumar
We present simple, user-friendly bounds for the expected operator norm of a random kernel matrix under general conditions on the kernel function . Our approach uses…
eess.IV2025
MANGO: Learning Disentangled Image Transformation Manifolds with Grouped Operators
Brighton Ancelin, Yenho Chen, Peimeng Guan +4
Learning semantically meaningful image transformations (i.e. rotation, thickness, blur) directly from examples can be a challenging task. Recently, the Manifold Autoencoder (MAE) p…