activity
20242026
collaborators

5 papers

cs.LG2026

Inverse problems with diffusion models: MAP estimation via mode-seeking loss

Sai Bharath Chandra Gutha, Ricardo Vinuesa, Hossein Azizpour

A pre-trained unconditional diffusion model, combined with posterior sampling or maximum a posteriori (MAP) estimation techniques, can solve arbitrary inverse problems without task…

physics.flu-dyn2025

Diff-SPORT: Diffusion-based Sensor Placement Optimization and Reconstruction of Turbulent flows in urban environments

Abhijeet Vishwasrao, Sai Bharath Chandra Gutha, Andres Cremades +6

Rapid urbanization demands accurate and efficient monitoring of turbulent wind patterns to support air quality, climate resilience and infrastructure design. Traditional sparse rec…

cs.CV2024

Inverse Problems with Diffusion Models: A MAP Estimation Perspective

Sai Bharath Chandra Gutha, Ricardo Vinuesa, Hossein Azizpour

Inverse problems have many applications in science and engineering. In Computer vision, several image restoration tasks such as inpainting, deblurring, and super-resolution can be…

cs.LG2024

Revisiting Score Function Estimators for -Subset Sampling

Klas Wijk, Ricardo Vinuesa, Hossein Azizpour

Are score function estimators an underestimated approach to learning with -subset sampling? Sampling -subsets is a fundamental operation in many machine learning tasks that i…

cs.LG2024

Indirectly Parameterized Concrete Autoencoders

Alfred Nilsson, Klas Wijk, Sai bharath chandra Gutha +7

Feature selection is a crucial task in settings where data is high-dimensional or acquiring the full set of features is costly. Recent developments in neural network-based embedded…