Yingzhen Li

We present an algorithm that learns the rate matrix of a continuous-time Markov chian to satisfy the Kolmogorov equation for sampling from unnormalised discrete distributions.

A solver-free approach for modelling stochastic differential equations using conditional normalising flows that enables direct sampling between arbitrary time points within trained horizon.

We present a new continual leanring method that builds and reuses compact memory for logistic regression

In this paper we introduce a framework to decompose the uncertainty of predictions in in-context learning