Continual learning aims to empower artificial intelligence (AI) with str...
Scaling sequence length has become a critical demand in the era of large...
To cope with real-world dynamics, an intelligent agent needs to incremen...
The input and output of most text generation tasks can be transformed to...
Prompts with different control signals (e.g., length, keywords, etc.) ca...
Significant improvement has been made on just noticeable difference (JND...
Continual learning requires incremental compatibility with a sequence of...
The base learners and labeled samples (shots) in an ensemble few-shot
cl...
In zero-shot multilingual extractive text summarization, a model is typi...
Continual learning needs to overcome catastrophic forgetting of the past...
Recently, various view synthesis distortion estimation models have been
...
Contrastive learning models have achieved great success in unsupervised
...
Recent progress of abstractive text summarization largely relies on larg...
As an important perceptual characteristic of the Human Visual System (HV...
Unsupervised extractive document summarization aims to select important
...
We propose a novel language-independent approach to improve the efficien...
Human identification is an important topic in event detection, person
tr...
Abstractive summarization aims to rewrite a long document to its shorter...
In zero-shot learning (ZSL), the samples to be classified are usually
pr...
Due to the deteriorated conditions of lack and uneven
lighting, nightti...
Graph representation learning aims to encode all nodes of a graph into
l...
As a metric to measure the performance of an online method, dynamic regr...
Different from Visual Question Answering task that requires to answer on...
Given a set of hand-crafted local features, acquiring a global represent...
Zero-shot learning (ZSL) has received extensive attention recently espec...
Zero-Shot Learning (ZSL) has received extensive attention and successes ...
Zero-shot learning (ZSL) has received increasing attention in recent yea...
Neural extractive summarization models usually employ a hierarchical enc...
Extractive summarization models need sentence level labels, which are us...
Sentence simplification aims to make sentences easier to read and unders...
Conventional graph-based dependency parsers guarantee a tree structure b...
Long Short-Term Memory (LSTM) networks, a type of recurrent neural netwo...