78 citations · 121 across the 9 of their papers we have counts for
3 papers · 1 filter
Deep Generative Models Strike Back! Improving Understanding and Evaluation in Light of Unmet Expectations for OoD Data
John Just, Sambuddha Ghosal
Advances in deep generative and density models have shown impressive capacity to model complex probability density functions in lower-dimensional space. Also, applying such models…
Encoding Invariances in Deep Generative Models
Viraj Shah, Ameya Joshi, Sambuddha Ghosal +4
Reliable training of generative adversarial networks (GANs) typically require massive datasets in order to model complicated distributions. However, in several applications, traini…
Anomalous diffusion in an electrolyte saturated paper matrix
Sankha Shuvra Das, Sumeet Kumar, Sambuddha Ghosal +2
Diffusion of colored dye on water saturated paper substrates has been traditionally exploited with great skill by renowned water color artists. The same physics finds more recent p…