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 Yutong Lu

Yutong Lu
Alert button

SAIH: A Scalable Evaluation Methodology for Understanding AI Performance Trend on HPC Systems


Dec 07, 2022
Jiangsu Du, Dongsheng Li, Yingpeng Wen, Jiazhi Jiang, Dan Huang, Xiangke Liao, Yutong Lu

Add code
Alert button

Figure 1 for SAIH: A Scalable Evaluation Methodology for Understanding AI Performance Trend on HPC Systems
Figure 2 for SAIH: A Scalable Evaluation Methodology for Understanding AI Performance Trend on HPC Systems
Figure 3 for SAIH: A Scalable Evaluation Methodology for Understanding AI Performance Trend on HPC Systems
Figure 4 for SAIH: A Scalable Evaluation Methodology for Understanding AI Performance Trend on HPC Systems
* 14 pages 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

EnergonAI: An Inference System for 10-100 Billion Parameter Transformer Models


Sep 06, 2022
Jiangsu Du, Ziming Liu, Jiarui Fang, Shenggui Li, Yongbin Li, Yutong Lu, Yang You

Add code
Alert button

Figure 1 for EnergonAI: An Inference System for 10-100 Billion Parameter Transformer Models
Figure 2 for EnergonAI: An Inference System for 10-100 Billion Parameter Transformer Models
Figure 3 for EnergonAI: An Inference System for 10-100 Billion Parameter Transformer Models
Figure 4 for EnergonAI: An Inference System for 10-100 Billion Parameter Transformer Models

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

LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking


Apr 19, 2022
Yupan Huang, Tengchao Lv, Lei Cui, Yutong Lu, Furu Wei

Add code
Alert button

Figure 1 for LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
Figure 2 for LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
Figure 3 for LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
Figure 4 for LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
* 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

A Picture is Worth a Thousand Words: A Unified System for Diverse Captions and Rich Images Generation


Oct 19, 2021
Yupan Huang, Bei Liu, Jianlong Fu, Yutong Lu

Add code
Alert button

Figure 1 for A Picture is Worth a Thousand Words: A Unified System for Diverse Captions and Rich Images Generation
Figure 2 for A Picture is Worth a Thousand Words: A Unified System for Diverse Captions and Rich Images Generation
Figure 3 for A Picture is Worth a Thousand Words: A Unified System for Diverse Captions and Rich Images Generation
* ACM MM 2021 (Video and Demo Track). Code: https://github.com/researchmm/generate-it 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Unifying Multimodal Transformer for Bi-directional Image and Text Generation


Oct 19, 2021
Yupan Huang, Hongwei Xue, Bei Liu, Yutong Lu

Add code
Alert button

Figure 1 for Unifying Multimodal Transformer for Bi-directional Image and Text Generation
Figure 2 for Unifying Multimodal Transformer for Bi-directional Image and Text Generation
Figure 3 for Unifying Multimodal Transformer for Bi-directional Image and Text Generation
Figure 4 for Unifying Multimodal Transformer for Bi-directional Image and Text Generation
* ACM MM 2021 (Industrial Track). Code: https://github.com/researchmm/generate-it 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Decoupling Localization and Classification in Single Shot Temporal Action Detection


Apr 16, 2019
Yupan Huang, Qi Dai, Yutong Lu

Add code
Alert button

Figure 1 for Decoupling Localization and Classification in Single Shot Temporal Action Detection
Figure 2 for Decoupling Localization and Classification in Single Shot Temporal Action Detection
Figure 3 for Decoupling Localization and Classification in Single Shot Temporal Action Detection
Figure 4 for Decoupling Localization and Classification in Single Shot Temporal Action Detection
* ICME 2019. https://github.com/HYPJUDY/Decouple-SSAD 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email