Pretrained language models have achieved remarkable success in a variety...
Video multimodal fusion aims to integrate multimodal signals in videos, ...
In-context learning (ICL) emerges as a promising capability of large lan...
With the increasing ability of large language models (LLMs), in-context
...
Large pretrained language models have shown surprising In-Context Learni...
Previous literature has proved that Pretrained Language Models (PLMs) ca...
The ability of pretrained Transformers to remember factual knowledge is
...
Fine-tuning pretrained language models (PLMs) on downstream tasks has be...
Sparse mixture of experts provides larger model capacity while requiring...
The Mixture-of-Experts (MoE) technique can scale up the model size of
Tr...
Biomedical Question Answering (BQA) has attracted increasing attention i...
Few-Shot Event Classification (FSEC) aims at developing a model for even...
Aspect Sentiment Triplet Extraction (ASTE) aims to recognize targets, th...
Large-scale pretrained language models are surprisingly good at recallin...
Conventional Machine Reading Comprehension (MRC) has been well-addressed...
Document-level Relation Extraction (RE) requires extracting relations
ex...
Conventional Knowledge Graph Completion (KGC) assumes that all test enti...
We introduce the task of automatic live commenting. Live commenting, whi...
Huge numbers of new words emerge every day, leading to a great need for
...
In this paper, we propose the task of live comment generation. Live comm...
The panoramic video is widely used to build virtual reality (VR) and is
...