14 citations · 24 across the 10 of their papers we have counts for
10 papers
Generating Visual Spatial Description via Holistic 3D Scene Understanding
Yu Zhao, Hao Fei, Wei Ji +4
Visual spatial description (VSD) aims to generate texts that describe the spatial relations of the given objects within images. Existing VSD work merely models the 2D geometrical v…
Non-parametric, Nearest-neighbor-assisted Fine-tuning for Neural Machine Translation
Jiayi Wang, Ke Wang, Yuqi Zhang +2
Non-parametric, k-nearest-neighbor algorithms have recently made inroads to assist generative models such as language models and machine translation decoders. We explore whether su…
From Alignment to Entailment: A Unified Textual Entailment Framework for Entity Alignment
Yu Zhao, Yike Wu, Xiangrui Cai +3
Entity Alignment (EA) aims to find the equivalent entities between two Knowledge Graphs (KGs). Existing methods usually encode the triples of entities as embeddings and learn to al…
A Note on the Strict Transformation of an Effective Cartier Divisor
Yu Zhao
Let be an effective Cartier divisor of a smooth variety . Let , be a set of pairwise disjoint smooth subvarieties in such that their union c…
Diffusion Models in NLP: A Survey
Yuansong Zhu, Yu Zhao
Diffusion models have become a powerful family of deep generative models, with record-breaking performance in many applications. This paper first gives an overview and derivation o…
An approximation to peak detection power using Gaussian random field theory
Yu Zhao, Dan Cheng, Armin Schwartzman
We study power approximation formulas for peak detection using Gaussian random field theory. The approximation, based on the expected number of local maxima above the threshold …