We developed a cloud-native, event-driven platform to scale Canto’s AI Visual Search to thousands of customers. Our solution supports large-scale processing of customer assets…
In the bot-with-plan project we developed an experimental approach to enhance the capabilities of ReAct-style LLM agents, particularly focusing on improving the performance of…
We built an internet search tool based on Retrieval-Augmented Generation (RAG) to answer natural language questions by searching the internet for relevant information and…
We have built the perceiver-io library, a modular implementation of the Perceiver family of model architectures (Perceiver, Perceiver IO, and Perceiver AR) in PyTorch. Our library…
In this project we provide an implementation for single image super-resolution, a process that is able to recover high-resolution images from low-resolution inputs as…
This is a comprehensive collection of notebooks about Bayesian methods for machine learning, like Bayesian regression, Gaussian processes, Bayesian optimization or variational inference in…
We built Eventuate, a toolkit for building applications with event-driven and event-sourced services. Eventuate enables services to communicate through causally ordered event streams, supporting…
We developed reboting.com, a framework for enhancing the accessibility and visualization of Austrian Open Data. Austrian Open Data: Visualizing geo-spatial information Our system integrates…