collaborators

5 papers

cs.LG2026

Lightweight Geometric Adaptation for Training Physics-Informed Neural Networks

Kang An, Chenhao Si, Shiqian Ma +1

Physics-Informed Neural Networks (PINNs) often suffer from slow convergence, training instability, and reduced accuracy on challenging partial differential equations due to the ani…

cs.CV2026

Ultra-low-light computer vision using trained photon correlations

Mandar M. Sohoni, Jérémie Laydevant, Mathieu Ouellet +7

Illumination using correlated photon sources has been established as an approach to allowing high-fidelity images to be reconstructed from noisy camera frames by taking advantage o…

stat.ML2026

Total Variation Rates for Riemannian Flow Matching

Yunrui Guan, Krishnakumar Balasubramanian, Shiqian Ma

Riemannian flow matching (RFM) extends flow-based generative modeling to data supported on manifolds by learning a time-dependent tangent vector field whose flow-ODE transports a s…

stat.ML2025

Mirror Flow Matching with Heavy-Tailed Priors for Generative Modeling on Convex Domains

Yunrui Guan, Krishnakumar Balasubramanian, Shiqian Ma

We study generative modeling on convex domains using flow matching and mirror maps, and identify two fundamental challenges. First, standard log-barrier mirror maps induce heavy-ta…

stat.ML2025

Riemannian Proximal Sampler for High-accuracy Sampling on Manifolds

Yunrui Guan, Krishnakumar Balasubramanian, Shiqian Ma

We introduce the Riemannian Proximal Sampler, a method for sampling from densities defined on Riemannian manifolds. The performance of this sampler critically depends on two key or…