We propose Riemannian Flow Matching (RFM), a simple yet powerful framework for training
continuous normalizing flows on manifolds. Existing methods for generative modeling on …

Selecting exploratory actions that generate a rich stream of experience for better learning is
a fundamental challenge in reinforcement learning (RL). An approach to tackle this problem …

Contrastive learning is a powerful self-supervised learning method, but we have a limited
theoretical understanding of how it works and why it works. In this paper, we prove that …

Unsupervised semantic segmentation is a long-standing challenge in computer vision with
great significance. Spectral clustering is a theoretically grounded solution to it where the …

Neural operators, as an efficient surrogate model for learning the solutions of PDEs, have
received extensive attention in the field of scientific machine learning. Among them, attention …

Self-predictive unsupervised learning methods such as BYOL or SimSIAM have shown
impressive results, and counter-intuitively, do not collapse to trivial representations. In this …

Self-supervised methods received tremendous attention thanks to their seemingly heuristic
approach to learning representations that respect the semantics of the data without any …

In standard supervised machine learning, it is necessary to provide a label for every input in
the data. While raw data in many application domains is easily obtainable on the Internet …

Many problems in causal inference and economics can be formulated in the framework of
conditional moment models, which characterize the target function through a collection of …

Non-contrastive self-supervised learning (NC-SSL) methods like BarlowTwins and VICReg
have shown great promise for label-free representation learning in computer vision. Despite …