Alert button
Picture for Duyu Tang

Duyu Tang

Alert button

Emage: Non-Autoregressive Text-to-Image Generation

Dec 22, 2023
Zhangyin Feng, Runyi Hu, Liangxin Liu, Fan Zhang, Duyu Tang, Yong Dai, Xiaocheng Feng, Jiwei Li, Bing Qin, Shuming Shi

Viaarxiv icon

SkillNet-X: A Multilingual Multitask Model with Sparsely Activated Skills

Jun 28, 2023
Zhangyin Feng, Yong Dai, Fan Zhang, Duyu Tang, Xiaocheng Feng, Shuangzhi Wu, Bing Qin, Yunbo Cao, Shuming Shi

Figure 1 for SkillNet-X: A Multilingual Multitask Model with Sparsely Activated Skills
Figure 2 for SkillNet-X: A Multilingual Multitask Model with Sparsely Activated Skills
Figure 3 for SkillNet-X: A Multilingual Multitask Model with Sparsely Activated Skills
Figure 4 for SkillNet-X: A Multilingual Multitask Model with Sparsely Activated Skills
Viaarxiv icon

Improved Visual Story Generation with Adaptive Context Modeling

May 26, 2023
Zhangyin Feng, Yuchen Ren, Xinmiao Yu, Xiaocheng Feng, Duyu Tang, Shuming Shi, Bing Qin

Figure 1 for Improved Visual Story Generation with Adaptive Context Modeling
Figure 2 for Improved Visual Story Generation with Adaptive Context Modeling
Figure 3 for Improved Visual Story Generation with Adaptive Context Modeling
Figure 4 for Improved Visual Story Generation with Adaptive Context Modeling
Viaarxiv icon

STOA-VLP: Spatial-Temporal Modeling of Object and Action for Video-Language Pre-training

Feb 20, 2023
Weihong Zhong, Mao Zheng, Duyu Tang, Xuan Luo, Heng Gong, Xiaocheng Feng, Bing Qin

Figure 1 for STOA-VLP: Spatial-Temporal Modeling of Object and Action for Video-Language Pre-training
Figure 2 for STOA-VLP: Spatial-Temporal Modeling of Object and Action for Video-Language Pre-training
Figure 3 for STOA-VLP: Spatial-Temporal Modeling of Object and Action for Video-Language Pre-training
Figure 4 for STOA-VLP: Spatial-Temporal Modeling of Object and Action for Video-Language Pre-training
Viaarxiv icon

Effidit: Your AI Writing Assistant

Aug 04, 2022
Shuming Shi, Enbo Zhao, Duyu Tang, Yan Wang, Piji Li, Wei Bi, Haiyun Jiang, Guoping Huang, Leyang Cui, Xinting Huang, Cong Zhou, Yong Dai, Dongyang Ma

Figure 1 for Effidit: Your AI Writing Assistant
Figure 2 for Effidit: Your AI Writing Assistant
Figure 3 for Effidit: Your AI Writing Assistant
Figure 4 for Effidit: Your AI Writing Assistant
Viaarxiv icon

One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code

May 12, 2022
Yong Dai, Duyu Tang, Liangxin Liu, Minghuan Tan, Cong Zhou, Jingquan Wang, Zhangyin Feng, Fan Zhang, Xueyu Hu, Shuming Shi

Figure 1 for One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code
Figure 2 for One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code
Figure 3 for One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code
Figure 4 for One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code
Viaarxiv icon

SkillNet-NLG: General-Purpose Natural Language Generation with a Sparsely Activated Approach

Apr 26, 2022
Junwei Liao, Duyu Tang, Fan Zhang, Shuming Shi

Viaarxiv icon

Pretraining Chinese BERT for Detecting Word Insertion and Deletion Errors

Apr 26, 2022
Cong Zhou, Yong Dai, Duyu Tang, Enbo Zhao, Zhangyin Feng, Li Kuang, Shuming Shi

Figure 1 for Pretraining Chinese BERT for Detecting Word Insertion and Deletion Errors
Figure 2 for Pretraining Chinese BERT for Detecting Word Insertion and Deletion Errors
Figure 3 for Pretraining Chinese BERT for Detecting Word Insertion and Deletion Errors
Figure 4 for Pretraining Chinese BERT for Detecting Word Insertion and Deletion Errors
Viaarxiv icon

MarkBERT: Marking Word Boundaries Improves Chinese BERT

Mar 12, 2022
Linyang Li, Yong Dai, Duyu Tang, Zhangyin Feng, Cong Zhou, Xipeng Qiu, Zenglin Xu, Shuming Shi

Figure 1 for MarkBERT: Marking Word Boundaries Improves Chinese BERT
Figure 2 for MarkBERT: Marking Word Boundaries Improves Chinese BERT
Figure 3 for MarkBERT: Marking Word Boundaries Improves Chinese BERT
Figure 4 for MarkBERT: Marking Word Boundaries Improves Chinese BERT
Viaarxiv icon

One Model, Multiple Tasks: Pathways for Natural Language Understanding

Mar 07, 2022
Duyu Tang, Fan Zhang, Yong Dai, Cong Zhou, Shuangzhi Wu, Shuming Shi

Figure 1 for One Model, Multiple Tasks: Pathways for Natural Language Understanding
Figure 2 for One Model, Multiple Tasks: Pathways for Natural Language Understanding
Figure 3 for One Model, Multiple Tasks: Pathways for Natural Language Understanding
Figure 4 for One Model, Multiple Tasks: Pathways for Natural Language Understanding
Viaarxiv icon