Neural network models have achieved state-of-the-art performances in a wide range of
natural language processing (NLP) tasks. However, a long-standing criticism against neural …

Plain text has become a prevalent interface for text-to-image synthesis. However, its limited
customization options hinder users from accurately describing desired outputs. For example …

Despite the remarkable success of large-scale Language Models (LLMs) such as GPT-3,
their performances still significantly underperform fine-tuned models in the task of text …

In this paper, we take the advantage of previous pre-trained models (PTMs) and propose a
novel Chinese pre-trained unbalanced transformer (CPT). Different from previous Chinese …

Text Classification is an important research area in natural language processing (NLP) that
has received a considerable amount of scholarly attention in recent years. However, real …

Node classification tasks aim to assign labels or categories to entire graphs based on their
structural properties or node attributes. It can be adopted for various types of graph systems …

Despite the success of ChatGPT, its performances on most NLP tasks are still well below the
supervised baselines. In this work, we looked into the causes, and discovered that its subpar …

Large-scale pretrained language models have achieved SOTA results on NLP tasks.
However, they have been shown vulnerable to adversarial attacks especially for logographic …

Inspired by the notion that``{\it to copy is easier than to memorize}``, in this work, we
introduce GNN-LM, which extends the vanilla neural language model (LM) by allowing to …

Micro-video classification plays a central role in online content recommendation platforms,
such as Kwai and Tik-Tok. Existing works on video classification largely exploit the …