Category: News

Featured article in Physics of Fluids (Letter): “Optimal navigation of magnetic artificial microswimmers in blood capillaries with deep reinforcement learning” July 1, 2025 Our letter appeared in Physics of Fluids as a featured article. Abstract Biomedical applications, such as targeted drug delivery, microsurgery, and sensing, rely on reaching precise areas within the body in a…Continue Reading Featured article in Physics of Fluids (Letter): “Optimal navigation of magnetic artificial microswimmers in blood capillaries with deep reinforcement learning”

New article in Journal of Fluid Mechanics: “Contactless precision steering of particles in a fluid inside a cube with rotating walls” June 30, 2025 This work demonstrates that ODIL can train control policies for path planning in real settings. We have built a robotic device (part of the winners at the massRobotics Form and Function challenge…Continue Reading New article in Journal of Fluid Mechanics: “Contactless precision steering of particles in a fluid inside a cube with rotating walls”

New publication in Physical Review Fluids: “Inertial focusing of spherical particles: The effects of rotational motion” March 14, 2025 The identification of cells and particles based on their transport properties in microfluidic devices is crucial for numerous applications in biology and medicine. Neutrally buoyant particles transported in microfluidic channels migrate laterally toward stable locations due…Continue Reading New publication in Physical Review Fluids: “Inertial focusing of spherical particles: The effects of rotational motion”

Our paper “Optimal Navigation in Microfluidics via the Optimization of a Discrete Loss” published in Physical Review Letters Semester: Spring | Year offered: 2021 | Link: Course Website Optimal path planning and control of microscopic devices navigating in fluid environments is essential for applications ranging from targeted drug delivery to environmental monitoring. These tasks are…Continue Reading Our paper “Optimal Navigation in Microfluidics via the Optimization of a Discrete Loss” published in Physical Review Letters

Quentin is joining us as a postdoctoral fellow from ETHZ. We’re very excited to combine his expertise on combustion and turbulence modeling with our ideas on closure models with reinforcement learning….Continue Reading Welcome to Quentin Malé!

Welcome to Christopher Suhamdy! January 29, 2025 We’re happy to welcome Christopher Suhamdy, a visiting student from Technical University of Munich ! Christopher will work on learning of effective dynamics for molecular systems….Continue Reading Welcome to Christopher Suhamdy!

Visit of Fei Sha from Google research We have the pleasure to welcome Fei Sha from Google research. Fei is visiting as an associate at Harvard, and we are excited to share ideas about generative AI and SciML….Continue Reading Visit of Fei Sha from Google research

Our paper “Generative learning for forecasting the dynamics of high-dimensional complex systems” is selected as Editor’s highlight in Nature Communications November 1, 2024 We introduce generative models for accelerating simulations of high-dimensional systems through learning and evolving their effective dynamics. In the proposed Generative Learning of Effective Dynamics (G-LED), instances of high dimensional data are…Continue Reading Our paper “Generative learning for forecasting the dynamics of high-dimensional complex systems” is selected as Editor’s highlight in Nature Communications

Visiting student Konstantinos Vogiatzoglou October 1, 2024 Welcome to Konstantinos Vogiatzoglou, visiting from the University of Tessali! We’re excited to work together on wild fire spread models and build upon our previous collaboration – An interpretable wildfire spreading model for real-time predictions….Continue Reading Visiting student Konstantinos Vogiatzoglou

Welcome to Rodrigo Abadia! September 15, 2024 We’re happy to have Rodrigo Abadia as a visiting student from Universidad Politecnica de Madrid! Rodrigo will work on incorporating conformal inferencewithin our learning the effective dynamics (LED) framework to quantify uncertainities in the predictions….Continue Reading Welcome to Rodrigo Abadia!