We describe a first step towards learning general-purpose visual
represe...
We investigate whether prompts learned independently for different tasks...
We study the geometry of linear networks with one-dimensional convolutio...
We introduce Train/Test-Time Adaptation with Retrieval (T^3AR), a
method...
We investigate compositional structures in vector data embeddings from
p...
We introduce À-la-carte Prompt Tuning (APT), a transformer-based scheme ...
We study the family of functions that are represented by a linear
convol...
In this note, we consider the optimization problem associated with compu...
We present Neural Splines, a technique for 3D surface reconstruction tha...
The critical locus of the loss function of a neural network is determine...
We present a theoretical and empirical study of the gradient dynamics of...
We study deep neural networks with polynomial activations, particularly ...
A set of fundamental matrices relating pairs of cameras in some configur...
We consider incidences among colored sets of lines in R^d and
examine wh...
Visual events in computer vision are studied from the perspective of
alg...
The rational camera model recently introduced in [19] provides a general...
We present a new framework for multi-view geometry in computer vision. A...