47 citations · 102 across the 15 of their papers we have counts for
15 papers
Ziya-Visual: Bilingual Large Vision-Language Model via Multi-Task Instruction Tuning
Junyu Lu, Dixiang Zhang, Xiaojun Wu +5
Recent advancements enlarge the capabilities of large language models (LLMs) in zero-shot image-to-text generation and understanding by integrating multi-modal inputs. However, suc…
MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentation
Jiaxing Zhang, Dongsheng Luo, Hua Wei
Graph Neural Networks (GNNs) have received increasing attention due to their ability to learn from graph-structured data. However, their predictions are often not interpretable. Po…
RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks
Jiaxing Zhang, Zhuomin Chen, Hao Mei +3
Graph regression is a fundamental task that has gained significant attention in various graph learning tasks. However, the inference process is often not easily interpretable. Curr…
UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective
Ping Yang, Junyu Lu, Ruyi Gan +4
We propose a new paradigm for universal information extraction (IE) that is compatible with any schema format and applicable to a list of IE tasks, such as named entity recognition…
Enhancing Text Generation with Cooperative Training
Tong Wu, Hao Wang, Zhongshen Zeng +3
Recently, there has been a surge in the use of generated data to enhance the performance of downstream models, largely due to the advancements in pre-trained language models. Howev…
Orca: A Few-shot Benchmark for Chinese Conversational Machine Reading Comprehension
Nuo Chen, Hongguang Li, Junqing He +8
The conversational machine reading comprehension (CMRC) task aims to answer questions in conversations, which has been a hot research topic in recent years because of its wide appl…
TCBERT: A Technical Report for Chinese Topic Classification BERT
Ting Han, Kunhao Pan, Xinyu Chen +5
Bidirectional Encoder Representations from Transformers or BERT~\cite{devlin-etal-2019-bert} has been one of the base models for various NLP tasks due to its remarkable performance…
Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective
Ping Yang, Junjie Wang, Ruyi Gan +6
We propose a new paradigm for zero-shot learners that is format agnostic, i.e., it is compatible with any format and applicable to a list of language tasks, such as text classifica…
Solving Math Word Problems via Cooperative Reasoning induced Language Models
Xinyu Zhu, Junjie Wang, Lin Zhang +4
Large-scale pre-trained language models (PLMs) bring new opportunities to challenging problems, especially those that need high-level intelligence, such as the math word problem (M…
MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model
Yatai Ji, Junjie Wang, Yuan Gong +6
Multimodal semantic understanding often has to deal with uncertainty, which means the obtained messages tend to refer to multiple targets. Such uncertainty is problematic for our i…
Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence
Jiaxing Zhang, Ruyi Gan, Junjie Wang +22
Nowadays, foundation models become one of fundamental infrastructures in artificial intelligence, paving ways to the general intelligence. However, the reality presents two urgent…
Unified BERT for Few-shot Natural Language Understanding
Junyu Lu, Ping Yang, Ruyi Gan +2
Even as pre-trained language models share a semantic encoder, natural language understanding suffers from a diversity of output schemas. In this paper, we propose UBERT, a unified…
BioBART: Pretraining and Evaluation of A Biomedical Generative Language Model
Hongyi Yuan, Zheng Yuan, Ruyi Gan +3
Pretrained language models have served as important backbones for natural language processing. Recently, in-domain pretraining has been shown to benefit various domain-specific dow…
Long Short-Term Sample Distillation
Liang Jiang, Zujie Wen, Zhongping Liang +7
In the past decade, there has been substantial progress at training increasingly deep neural networks. Recent advances within the teacher--student training paradigm have establishe…
Accelerating Reinforcement Learning with a Directional-Gaussian-Smoothing Evolution Strategy
Jiaxing Zhang, Hoang Tran, Guannan Zhang
Evolution strategy (ES) has been shown great promise in many challenging reinforcement learning (RL) tasks, rivaling other state-of-the-art deep RL methods. Yet, there are two limi…