Eric P. Xing

TL;DR: In this article, a hybrid retrieval-generation reinforced agent (HRGR-Agent) is proposed to achieve structured, robust, and diverse report generation by employing a hierarchical decision-making procedure.

TL;DR: This paper proposes an extension of State Space Model to work with different sources of information together with its learning and inference algorithms and applies this model to decode the mind state of students during lectures based on their brain waves and reaches a significant better results compared to traditional methods.

TL;DR: In this paper, the authors proposed Vicinal Labels Under Uncertainty (VLUU), a simple yet efficient framework utilizing the human structure similarity for partially supervised medical image segmentation, which transforms the partially supervised problem into a fully supervised problem by generating vicinal labels.

TL;DR: Prior swapping as mentioned in this paper leverages the pre-inferred false posterior to efficiently generate accurate posterior samples under arbitrary target priors, which can be used to apply less-costly inference algorithms to certain models, and incorporate new or updated prior information "post-inference".

TL;DR: A new encoding heuristic of the input symbols for character-level NLP models is introduced: it encodes the shape of each character through the images depicting the letters when printed, expected to improve the robustness of N LP models.