Google's PaLM 2 gets better at math when you let the language model take a breather.

In a paper, researchers have investigated whether language models such as GPT-4 or PaLM 2 are suitable as optimizers that automatically find solutions to predefined problems, such as recommending movies or solving grade school math problems.

The language models tried to find the best prompts for each task on their own. The prompt that PaLM 2-L used particularly well to solve math problems was curious: "Take a deep breath and work on this problem step-by-step." Without taking a deep breath, accuracy dropped by almost ten points.

CityDreamer, a generative AI model, creates unbounded 3D cities by separating the generation of building instances from other background objects. This model allows for better handling of the diverse appearance of buildings in urban environments - one of the main challenges compared to generating natural environments, as methods such as GANCraft do.

To enhance the realism of the generated 3D cities, the authors constructed two datasets, OSM and GoogleEarth, which provide more realistic city layouts and appearances, easily scalable to other cities worldwide.