A new study by Shanghai Jiao Tong University and SII Generative AI Research Lab (GAIR) shows that training large language models (LLMs) for complex, autonomous tasks does not require massive datasets.

Abstract: Adversarial attacks craft adversarial examples (AEs) to fool convolution neural networks. The mainstream gradient-based attacks, based on first-order optimization methods, encounter ...

The problem of the region of stability of the fourth order-Runge-Kutta method for the solution of systems of differential equations is studied. This region can be characterized by means of linear ...

This repository contains information and code to reproduce the results presented in the article Using a recent characterization of energy-preserving B-series, we derive the explicit conditions on the ...

In this organization, you can find the code for problems I solved for the Numerical Mathematics course. The code is written in Julia, and the tasks are provided here link to the Assignments. For a ...

Reduction in forest resources due to increasing global warming and population growth is a critical situation the World faces today. As these reserves decrease, it alarms new challenges that require ...

Department on Applied Mathematics, Instituto Universitario de Física Fundamental y Matemáticas, Universidad de Salamanca, Salamanca, Spain These types of problems are very common in a large amount of ...