Research Action Space Design – Reinforcement Learning for Robot Motor Skills 09. April 2025 Practitioners typically rely on intuition to choose action spaces for robot learning tasks. This study examines action space selection across various tasks and robots, offering practical guidelines for the robot learning community.... read more
Research Splitting Stump Forests: A Model to Accurately “Compress”? 19. March 2025 Edge AI enables local AI model deployment for efficient data processing, but optimization is challenging. This post explores Splitting Stump Forests (SSF), a powerful compression technique for efficient Edge AI deployment. ... read more
Research Can Stories Help LLMs Reason? A Deep Dive into the Story of Thought (SoT) Framework 11. December 2024 Can storytelling unlock new reasoning powers in AI? Explore how the innovative Story of Thought (SoT) framework uses narratives to enhance LLMs' ability to solve complex, knowledge-intensive problems with greater coherence and depth.... read more
Research Multilingual Instruction-Tuning: Do Polyglot Models Demand for Multilingual Instructions? 30. October 2024 Multilingual instruction-tuning of models pre-trained on Indo-European languages reveals that (semantically) parallel datasets significantly boost cross-lingual capabilities compared to monolingual ones. We introduce new multilingual evaluation resources and datasets for polyglot model training. ... read more
Research qubolite: A Toolbox for Working with QUBO 31. January 2024 Quadratic unconstrained binary optimization (QUBO) problems appear in many different domains such as Machine Learning and Data Mining. We present our light-weight and feature-rich Python package qubolite for working with QUBO.... read more
Research Simplified language for all: How to create a dataset in Simple German 06. December 2023 Machine Learning models are only as diverse as the datasets they are trained on. Learn more about the first publicly available bilingual dataset in German and Simple German language provided by us.... read more
Research Guided Reinforcement Learning – Deployed for Dynamic Locomotion of a Two-Wheeled Robot 04. October 2023 Guided RL aims at learning control policies for real-world robots in an efficient and effective way. We showcase how to practically apply it to the task of learning dynamic locomotion for a two-wheeled robot.... read more
Research Guided Reinforcement Learning – Application to three Robotic Tasks 26. July 2023 Guided RL aims at learning control policies for real world robots in an efficient and effective way. We showcase how the introduced modular toolbox can be applied to three different robotic tasks.... read more
Research Guided Reinforcement Learning – Towards Efficient and Effective Real-World Robotics 12. July 2023 Guided Reinforcement Learning describes a concept for learning control policies of intelligent robots. By incorporating additional knowledge, the training process becomes more data-efficient and effective for real-world robotics.... read more
