Gunhee Kim

TL;DR: A scalable and parallelizable sequential Monte Carlo based method is developed to construct the similarity network of a large-scale dataset that provides a base representation for wide ranges of dynamics analysis.

TL;DR: It is found that existing fact checking systems that perform well on claims in formal style significantly degenerate on colloquial claims with the same semantics, and it is shown that document retrieval is the weakest spot in the system even vulnerable to filler words, such as “yeah” and “you know”.

TL;DR: This work proposes ESPER, a novel approach to reinforcement learning which extends language-only zero-shot models to unseen multimodal tasks, like image and audio captioning, and demonstrates that it outperforms baselines and prior work on a variety of zero- shot tasks.

TL;DR: This work proposes novel training schemes with a new set of losses named moment reconstruction losses that simply replace the reconstruction loss that are applicable to any conditional generation tasks by performing thorough experiments on image-to-image translation, super-resolution and image inpainting using Cityscapes and CelebA dataset.