From February 2 to February 4, EDI colleagues: software engineers Guntis Vilnis Strazds and Rebeka Birziņa, researcher Laura Leja, and senior researcher Dr. sc. comp Kārlis Freivalds participated in the Workshop on Uncertainty in Machine Learning (WUML 2026), which this year takes place University of Tartu, Estonia.
In recent years, the importance of uncertainty has increased due to the increasing role of machine learning in practical applications, many of which have specific security requirements. The goal of this workshop is to bring together researchers interested in the topic of uncertainty in machine learning and to provide a forum to discuss the latest advances in modeling and quantifying machine learning problems, as well as to explore new research directions in this area.
Dr. sc. comp. Kārlis Freivalds gave a presentation talk at this seminar: “Solving Boolean Satisfiability by Repeated Knowledge Accumulation”, while other participated in the poster session, presenting results from various EDI projects:
- Guntis Vilnis Strazds – “Harnessing Foundation Models to Generate and Verify Robot Control Policies”;
- Rebeka Birziņa – “Test Time Scaling Methods For Neural SAT Solve”;
- and Laura Leja – “Shaping Flames with Differentiable Physics Simulations”.
More information about the workshop can be found here: https://sites.google.com/view/wuml2026/homec
