News
-
Gave a talk on “An analytic theory of convolutional neural network inverse problems solvers” at the Workshop on Principles and Methods in Generative Modeling of Complex Processes at IRIT, Toulouse.
-
Co-organizing the new edition of the DeepInverse hackathon at CIRM, Marseille, 30 August – 2 September 2026, as one of the library’s maintainers.
-
I will be attending ICML 2026 in Seoul, South Korea, 8–14 July. Come say hello at our poster — happy to chat about collaborations or research ideas.
-
Attending the Peyresq 26 summer school on generative models: a week of lectures and tutorials on diffusion models, flow matching and optimal transport.
-
Our paper “A Morse-Bott Framework for Blind Inverse Problems: Local Recovery Guarantees and the Failure of the MAP” has been accepted in the SIAM Journal on Imaging Sciences (SIIMS).
-
Our paper “An analytic theory of convolutional neural network inverse problems solvers” has been accepted at ICML 2026.
-
With Andrew Wang, presenting DeepInverse at the PyTorch Conference Europe 2026 in Paris.
-
New preprint: “An analytic theory of convolutional neural network inverse problems solvers”. Under two structural constraints (translation equivariance and locality), we derive closed-form, interpretable expressions for trained CNN solvers and validate them across architectures and inverse problems.
-
DeepInverse is now officially part of the PyTorch Ecosystem.
-
New preprint: “A Morse-Bott Framework for Blind Inverse Problems: Local Recovery Guarantees and the Failure of the MAP”, studying blind deconvolution with state-of-the-art diffusion priors.
-
Representing the DeepInverse community to receive the Open Science Prize from the French Ministry of Higher Education and Research.
-
New preprint: “Comparing Plug-and-Play and Unrolled networks” — a review of both approaches in a Bayesian framework, relating each to a statistical estimator.
-
Participating in the DeepInverse hackathon at CIRM, Marseille, 28–29 October 2024: two days with contributors from across Europe adding imaging operators and diffusion samplers to DeepInverse.
-
Our paper “DeepVibes: Correcting Micro-Vibrations in Satellite Imaging with Pushbroom Cameras” has been accepted in IEEE Transactions on Geoscience and Remote Sensing.