Eric P. Xing

TL;DR: The Zero-shot Manipulation Net (ZM-Net) is proposed, a fully-differentiable architecture that jointly optimizes an image-transformation network (TNet) and a parameter network (PNet) that performs fast zero-shot image manipulation according to both signal-dependent parameters from the PNet and signal-invariant parameters fromThe TNet itself.

TL;DR: Quantitative and human evaluations show the proposed structured approach to imposing conversational goals on open-domain chat agents can produce meaningful and effective conversations, significantly improving over other approaches.

TL;DR: This work derives an optimization problem for estimating (alternative) parameters of a latent tree graphical model, allowing it to represent the marginal probability table of the observed variables in a compact and robust way, and derives a novel decomposition based on this framework.

TL;DR: A dynamic Bayesian model for motifs in biopolymer sequences which captures rich biological prior knowledge and positional dependencies in motif structure in a principled way is proposed and has much higher sensitivity to motifs during detection and a notable ability to distinguish genuine motifs from false recurring patterns.

TL;DR: A new topic model is proposed that incorporates a hidden variable to control a pivot language, in an extension of CorrLDA, that is more effective than some other existing multilingual topic models.