1 citations · 1 across the 4 of their papers we have counts for
Showing 2024Show all
2 papers · 1 filter
cs.LG2024
Non-equilibrium active noise enhances generative memory in diffusion models
Agnish Kumar Behera, Alexandra Lamtyugina, Aditya Nandy +3
Generative diffusion models have emerged as powerful tools for sampling high-dimensional distributions, yet they typically rely on white gaussian noise and noise schedules to destr…
cond-mat.dis-nn2024
A correspondence between Hebbian unlearning and steady states generated by nonequilibrium dynamics
Agnish Kumar Behera, Matthew Du, Uday Jagadisan +3
The classic paradigms for learning and memory recall focus on strengths of synaptic couplings and how these can be modulated to encode memories. In a previous paper [A. K. Behera,…