Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Discrete Langevin-Inspired Posterior Sampling
Chaitanya Amballa, Sattwik Basu, Jorge Vančo Sampedro +1
We study posterior sampling for inverse problems in discrete state spaces using discrete diffusion models as generative priors. While continuous diffusion models have become widely…
cs.LG2025
Learning Energy-based Variational Latent Prior for VAEs
Debottam Dutta, Chaitanya Amballa, Zhongweiyang Xu +2
Variational Auto-Encoders (VAEs) are known to generate blurry and inconsistent samples. One reason for this is the "prior hole" problem. A prior hole refers to regions that have hi…