Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Zhihao Fan

Zhihao Fan
Alert button

Unifying Structure Reasoning and Language Model Pre-training for Complex Reasoning


Jan 21, 2023
Siyuan Wang, Zhongyu Wei, Jiarong Xu, Zhihao Fan

Add code
Alert button

Figure 1 for Unifying Structure Reasoning and Language Model Pre-training for Complex Reasoning
Figure 2 for Unifying Structure Reasoning and Language Model Pre-training for Complex Reasoning
Figure 3 for Unifying Structure Reasoning and Language Model Pre-training for Complex Reasoning
Figure 4 for Unifying Structure Reasoning and Language Model Pre-training for Complex Reasoning
* 10 pages, 4 figures, 6 tables 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

GENIE: Large Scale Pre-training for Text Generation with Diffusion Model


Dec 22, 2022
Zhenghao Lin, Yeyun Gong, Yelong Shen, Tong Wu, Zhihao Fan, Chen Lin, Weizhu Chen, Nan Duan

Add code
Alert button

Figure 1 for GENIE: Large Scale Pre-training for Text Generation with Diffusion Model
Figure 2 for GENIE: Large Scale Pre-training for Text Generation with Diffusion Model
Figure 3 for GENIE: Large Scale Pre-training for Text Generation with Diffusion Model
Figure 4 for GENIE: Large Scale Pre-training for Text Generation with Diffusion Model
* Work in progress 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report


Nov 07, 2022
Andrey Ignatov, Radu Timofte, Shuai Liu, Chaoyu Feng, Furui Bai, Xiaotao Wang, Lei Lei, Ziyao Yi, Yan Xiang, Zibin Liu, Shaoqing Li, Keming Shi, Dehui Kong, Ke Xu, Minsu Kwon, Yaqi Wu, Jiesi Zheng, Zhihao Fan, Xun Wu, Feng Zhang, Albert No, Minhyeok Cho, Zewen Chen, Xiaze Zhang, Ran Li, Juan Wang, Zhiming Wang, Marcos V. Conde, Ui-Jin Choi, Georgy Perevozchikov, Egor Ershov, Zheng Hui, Mengchuan Dong, Xin Lou, Wei Zhou, Cong Pang, Haina Qin, Mingxuan Cai

Add code
Alert button

Figure 1 for Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report
Figure 2 for Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report
Figure 3 for Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report
Figure 4 for Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering


Aug 22, 2022
Siyuan Wang, Zhongyu Wei, Zhihao Fan, Qi Zhang, Xuanjing Huang

Add code
Alert button

Figure 1 for Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering
Figure 2 for Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering
Figure 3 for Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering
Figure 4 for Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering
* 11 pages, 6 figures, 6 tables, accepted as a long paper to COLING 2022 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A Unified Continuous Learning Framework for Multi-modal Knowledge Discovery and Pre-training


Jun 11, 2022
Zhihao Fan, Zhongyu Wei, Jingjing Chen, Siyuan Wang, Zejun Li, Jiarong Xu, Xuanjing Huang

Add code
Alert button

Figure 1 for A Unified Continuous Learning Framework for Multi-modal Knowledge Discovery and Pre-training
Figure 2 for A Unified Continuous Learning Framework for Multi-modal Knowledge Discovery and Pre-training
Figure 3 for A Unified Continuous Learning Framework for Multi-modal Knowledge Discovery and Pre-training
Figure 4 for A Unified Continuous Learning Framework for Multi-modal Knowledge Discovery and Pre-training

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

MVP: Multi-Stage Vision-Language Pre-Training via Multi-Level Semantic Alignment


Jan 29, 2022
Zejun Li, Zhihao Fan, Huaixiao Tou, Zhongyu Wei

Add code
Alert button

Figure 1 for MVP: Multi-Stage Vision-Language Pre-Training via Multi-Level Semantic Alignment
Figure 2 for MVP: Multi-Stage Vision-Language Pre-Training via Multi-Level Semantic Alignment
Figure 3 for MVP: Multi-Stage Vision-Language Pre-Training via Multi-Level Semantic Alignment
Figure 4 for MVP: Multi-Stage Vision-Language Pre-Training via Multi-Level Semantic Alignment

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Negative Sample is Negative in Its Own Way: Tailoring Negative Sentences for Image-Text Retrieval


Nov 05, 2021
Zhihao Fan, Zhongyu Wei, Zejun Li, Siyuan Wang, Jianqing Fan

Add code
Alert button

Figure 1 for Negative Sample is Negative in Its Own Way: Tailoring Negative Sentences for Image-Text Retrieval
Figure 2 for Negative Sample is Negative in Its Own Way: Tailoring Negative Sentences for Image-Text Retrieval
Figure 3 for Negative Sample is Negative in Its Own Way: Tailoring Negative Sentences for Image-Text Retrieval
Figure 4 for Negative Sample is Negative in Its Own Way: Tailoring Negative Sentences for Image-Text Retrieval

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain Conversations


Sep 24, 2021
Wei Chen, Yeyun Gong, Can Xu, Huang Hu, Bolun Yao, Zhongyu Wei, Zhihao Fan, Xiaowu Hu, Bartuer Zhou, Biao Cheng, Daxin Jiang, Nan Duan

Add code
Alert button

Figure 1 for Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain Conversations
Figure 2 for Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain Conversations
Figure 3 for Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain Conversations
Figure 4 for Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain Conversations

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Constructing Phrase-level Semantic Labels to Form Multi-Grained Supervision for Image-Text Retrieval


Sep 12, 2021
Zhihao Fan, Zhongyu Wei, Zejun Li, Siyuan Wang, Haijun Shan, Xuanjing Huang, Jianqing Fan

Add code
Alert button

Figure 1 for Constructing Phrase-level Semantic Labels to Form Multi-Grained Supervision for Image-Text Retrieval
Figure 2 for Constructing Phrase-level Semantic Labels to Form Multi-Grained Supervision for Image-Text Retrieval
Figure 3 for Constructing Phrase-level Semantic Labels to Form Multi-Grained Supervision for Image-Text Retrieval
Figure 4 for Constructing Phrase-level Semantic Labels to Form Multi-Grained Supervision for Image-Text Retrieval

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

TCIC: Theme Concepts Learning Cross Language and Vision for Image Captioning


Jun 21, 2021
Zhihao Fan, Zhongyu Wei, Siyuan Wang, Ruize Wang, Zejun Li, Haijun Shan, Xuanjing Huang

Add code
Alert button

Figure 1 for TCIC: Theme Concepts Learning Cross Language and Vision for Image Captioning
Figure 2 for TCIC: Theme Concepts Learning Cross Language and Vision for Image Captioning
Figure 3 for TCIC: Theme Concepts Learning Cross Language and Vision for Image Captioning
Figure 4 for TCIC: Theme Concepts Learning Cross Language and Vision for Image Captioning
* IJCAI2021 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>