We present a novel approach for structured data-to-text generation that
...
Recent advances in foundation models present new opportunities for
inter...
Entities can be expressed in diverse formats, such as texts, images, or
...
This paper investigates the capabilities of Large Language Models (LLMs)...
We introduce STREET, a unified multi-task and multi-domain natural langu...
A central challenge of building more powerful Graph Neural Networks (GNN...
Language models (LMs) are becoming the foundation for almost all major
l...
Learning skills from language provides a powerful avenue for generalizat...
Question answering over knowledge bases (KBs) aims to answer natural lan...
Many animals and humans process the visual field with a varying spatial
...
In open question answering (QA), the answer to a question is produced by...
The open-source and community-supported gem5 simulator is one of the mos...
Generative adversarial networks (GANs) learn the distribution of observe...
Existing question answering datasets focus on dealing with homogeneous
i...
There are two main lines of research on visual reasoning: neural module
...
Modelling relations between multiple entities has attracted increasing
a...
With the rapid development in deep learning, deep neural networks have b...
Despite the great success object detection and segmentation models have
...
With the recent surge of interests in deep neural networks, more real-wo...
Many knowledge graph embedding methods operate on triples and are theref...
Inferring missing links in knowledge graphs (KG) has attracted a lot of
...
The discriminative approach to classification using deep neural networks...