by Vancho Kocevski | Jul 14, 2026
This project will develop a pre-silicon framework for evaluating arithmetic reliability in scientific computing hardware. The project will help hardware designers determine which arithmetic blocks are most vulnerable to silent data corruption, what protections cost in...
by Vancho Kocevski | Jul 14, 2026
This project will develop interpretable machine-learning models that combine programmatic features with simple predictors for scientific modeling tasks. The project will extend the LeaPR framework to climate science, materials science and neuroscience, with the goal...
by Vancho Kocevski | Jul 14, 2026
This project will develop new algorithms and hardware for solving combinatorial optimization problems. The team will expand its relaxation-oscillator-based SAT-solver hardware and algorithms to broader classes of optimization problems, with multiple-input,...
by Vancho Kocevski | Jul 14, 2026
This project will develop an uncertainty-aware, physics-guided AI framework for the design of photonic and phononic topological metamaterials. Their approach will combine generative design, fast surrogate models, uncertainty quantification and high-fidelity...
by Vancho Kocevski | Jul 14, 2026
This project will develop methods to fine-tune foundational machine-learning interatomic potentials using experimental phase diagram data. The approach aims to overcome known limitations of density functional theory for rare-earth and actinide materials, enabling more...
by Vancho Kocevski | Jul 14, 2026
This project will integrate mobile robotic automation into the SALSA self-driving laboratory to support battery electrolyte discovery. The project will develop safe robotic manipulation policies for handling delicate glassware, a multi-physics digital twin that models...
by Vancho Kocevski | Jul 14, 2026
This project will develop computational imaging methods to reconstruct and track the behavior of freely moving fruit flies across long, multiview video recordings. The project will use conditional Gaussian splatting-based 4D reconstruction to identify behavioral...
by Vancho Kocevski | Jul 14, 2026
This project will develop a flow-matching approach to detect and characterize galaxy clusters directly from telescope images. Their method will bypass intermediate galaxy catalogs and instead deliver probabilistic estimates of cluster properties such as mass, redshift...
