Sort by
Refine Your Search
-
Vision–Language–Action (VLA) models for tabletop and mobile manipulation. A key focus is leveraging whole-body, humanoid-style motion to improve perception and control, enabling robots to solve complex
-
with a strong background in machine learning and LLMs, computer science, and modeling. The candidate will join the project “AI-driven predictive maintenance for buildings: Einar Mattsson (EM) - KTH
-
to extract knowledge from data, modelling large-scale complex systems, and exploring new application areas in data science. Areas of interest include but are not limited to models and algorithms for knowledge
-
such as spectrally controlled reflectivity and transmission, down conversion, light trapping and light extraction, nonlinear effects, and solar cells. The work involves electromagnetic modeling