Probabilistic solvers provide a flexible and efficient framework for simulation, uncertainty quantification, and inference in dynamical systems.

In many unpaired image domain translation problems, e.g., style transfer or super-resolution, it is important to keep the translated image similar to its respective input image.

Figure 1: Image of a Brown Thrasher and how the ProtoPool (left) and ProtoPool-Concepts (ours, right) explain their decisions. Prototype classifications are made by finding patches in the image similar to learned prototypical parts. Single-visualization methods such as ProtoPool can make visually ambiguous decisions when the semantic features underlying a prototype are unclear.

Precise mass location and extent (e.g., mass boundaries) are typically not available in the patient's records, and it is burdensome, error-prone, and sometimes impossible to

Transformer neural networks can exhibit a surprising capacity for in-context learning (ICL) despite not being explicitly trained for it.

We refer to the proposed solution as SA3D, for Segment Anything in 3D. It is only required to provide a manual segmentation prompt ( e.g., rough points) for the target object in a single view, which is used to generate its 2D mask in this view with SAM.