Deep Generative Models on Home https://shashankkroy.github.io/tags/deep-generative-models/ Recent content in Deep Generative Models on Home Hugo -- gohugo.io en Mon, 07 Sep 2026 00:00:00 +0000 flow-matching: From first principals to building new algorithms https://shashankkroy.github.io/projects/flow-matching/ Mon, 07 Sep 2026 00:00:00 +0000 https://shashankkroy.github.io/projects/flow-matching/ The notes will end abruptly at a point when I shift to overleaf for the manuscript Flow matching for posterior sampling in variational data assimilation Open
flow matching generative models Bayesian inference variational DA

Variational data assimilation gives a mode of the posterior; generative models can give samples. This project investigates bridging variational assimilation with flow matching so that the assimilation system produces genuine posterior samples — the direction I presented at the EnKF Workshop 2026.

Literature & running notes

30 Aug 2026

EnKF Workshop 2026 talk — Bridging Variational DA and Flow Matching for Posterior Sampling

My talk sketching the connection; the project is to develop this into a working method on a quasi-geostrophic testbed and compare against ensemble Kalman baselines.

References

https://arxiv.org/abs/2510.02952

Concepts for interpretability, physical guidance in models

Concept bottleneck models (CBMs) offer a middle ground by routing predictions through an intermediate layer of interpretable concepts. They structurally embed physical reasoning into the model without over-constraining it. Tp recover the mechanistic drivers of marine heatwaves (MHWs) through prescribed concepts and a free concept that captures residual structure and regularizes prescription. By combining mixed supervision with an ensemble of CBMs, OceanCBM balances physical constraint, flexibility, and mechanistic interpretability. https://arxiv.org/pdf/2605.12639

]]>