This short abstract describes a solution to the COSAS 2024 competition on Cross-Organ and Cross-Scanner Adenocarcinoma Segmentation from histopathological image patches. The main challenge in the task of segmenting this type of cancer is a noticeable domain shift encountered when changing acquisition devices (microscopes) and also when tissue comes from different organs. The two tasks proposed in COSAS were to train on a dataset of images from three different organs, and then predict segmentations on data from unseen organs (dataset T1), and to train on a dataset of images acquired on three different scanners and then segment images acquired with another unseen microscope. We attempted to bridge the domain shift gap by experimenting with three different strategies: standard training for each dataset, pretraining on dataset T1 and then fine-tuning on dataset T2 (and vice-versa, a strategy we call \textit{Cross-Task Pretraining}), and training on the combination of dataset A and B. Our experiments showed that Cross-Task Pre-training is a more promising approach to domain generalization.

For the last three years, the AutoPET competition gathered the medical imaging community around a hot topic: lesion segmentation on Positron Emitting Tomography (PET) scans. Each year a different aspect of the problem is presented; in 2024 the multiplicity of existing and used tracers was at the core of the challenge. Specifically, this year's edition aims to develop a fully automatic algorithm capable of performing lesion segmentation on a PET/CT scan, without knowing the tracer, which can either be a FDG or PSMA-based tracer. In this paper we describe how we used the nnUNetv2[1] framework to train two sets of 6 fold ensembles of models to perform fully automatic PET/CT lesion segmentation as well as a MIP-CNN to choose which set of models to use for segmentation.

We assess the ability of GPT -- a large language model -- to serve as a financial robo-advisor for the masses, by using a financial literacy test. Davinci and ChatGPT based on GPT-3.5 score 66% and 65% on the financial literacy test, respectively, compared to a baseline of 33%. However, ChatGPT based on GPT-4 achieves a near-perfect 99% score, pointing to financial literacy becoming an emergent ability of state-of-the-art models. We use the Judge-Advisor System and a savings dilemma to illustrate how researchers might assess advice-utilization from large language models. We also present a number of directions for future research.

A mobility map, which provides maximum achievable speed on a given terrain, is essential for path planning of autonomous ground vehicles in off-road settings. While physics-based simulations play a central role in creating next-generation, high-fidelity mobility maps, they are cumbersome and expensive. For instance, a typical simulation can take weeks to run on a supercomputer and each map requires thousands of such simulations. Recent work at the U.S. Army CCDC Ground Vehicle Systems Center has shown that trained machine learning classifiers can greatly improve the efficiency of this process. However, deciding which simulations to run in order to train the classifier efficiently is still an open problem. According to PAC learning theory, data that can be separated by a classifier is expected to require $\mathcal{O}(1/\epsilon)$ randomly selected points (simulations) to train the classifier with error less than $\epsilon$. In this paper, building on existing algorithms, we introduce an active learning paradigm that substantially reduces the number of simulations needed to train a machine learning classifier without sacrificing accuracy. Experimental results suggest that our sampling algorithm can train a neural network, with higher accuracy, using less than half the number of simulations when compared to random sampling.

A company operating a website on how to prepare for qualification examinations is using artificial intelligence (AI) to successfully predict questions on such tests. Tokyo-based Sight Visit Inc. correctly picked 57 out of 95 questions -- about 60% -- that went on the multiple choice section of the preliminary test for the state bar examination in May. One of the questions that the company correctly predicted is a true-or-false one that stated: "When deciding to involve an expert commissioner when preparing to hold oral proceedings to hear explanations based on their expert knowledge, the opinions of the concerned parties must be heard." Sight Visit deems that it has been successful when its predictions for both questions and their answer options are totally, or almost, correct. The preliminary test for the state bar exam comprises multiple choice and description-type sections.