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 Pu Zhao

Pu Zhao
Alert button

Less is More: Data Pruning for Faster Adversarial Training


Feb 28, 2023
Yize Li, Pu Zhao, Xue Lin, Bhavya Kailkhura, Ryan Goldhahn

Add code
Alert button

Figure 1 for Less is More: Data Pruning for Faster Adversarial Training
Figure 2 for Less is More: Data Pruning for Faster Adversarial Training
Figure 3 for Less is More: Data Pruning for Faster Adversarial Training
Figure 4 for Less is More: Data Pruning for Faster Adversarial Training
* The AAAI-23 Workshop on Artificial Intelligence Safety (SafeAI 2023) 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Retrieval


Feb 06, 2023
Ziyang luo, Pu Zhao, Can Xu, Xiubo Geng, Tao Shen, Chongyang Tao, Jing Ma, Qingwen lin, Daxin Jiang

Add code
Alert button

Figure 1 for LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Retrieval
Figure 2 for LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Retrieval
Figure 3 for LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Retrieval
Figure 4 for LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale 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

All-in-One: A Highly Representative DNN Pruning Framework for Edge Devices with Dynamic Power Management


Dec 09, 2022
Yifan Gong, Zheng Zhan, Pu Zhao, Yushu Wu, Chao Wu, Caiwen Ding, Weiwen Jiang, Minghai Qin, Yanzhi Wang

Add code
Alert button

Figure 1 for All-in-One: A Highly Representative DNN Pruning Framework for Edge Devices with Dynamic Power Management
Figure 2 for All-in-One: A Highly Representative DNN Pruning Framework for Edge Devices with Dynamic Power Management
Figure 3 for All-in-One: A Highly Representative DNN Pruning Framework for Edge Devices with Dynamic Power Management
Figure 4 for All-in-One: A Highly Representative DNN Pruning Framework for Edge Devices with Dynamic Power Management

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

MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation


Nov 16, 2022
Jiazhan Feng, Qingfeng Sun, Can Xu, Pu Zhao, Yaming Yang, Chongyang Tao, Dongyan Zhao, Qingwei Lin

Add code
Alert button

Figure 1 for MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation
Figure 2 for MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation
Figure 3 for MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation
Figure 4 for MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation

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

Advancing Model Pruning via Bi-level Optimization


Oct 12, 2022
Yihua Zhang, Yuguang Yao, Parikshit Ram, Pu Zhao, Tianlong Chen, Mingyi Hong, Yanzhi Wang, Sijia Liu

Add code
Alert button

Figure 1 for Advancing Model Pruning via Bi-level Optimization
Figure 2 for Advancing Model Pruning via Bi-level Optimization
Figure 3 for Advancing Model Pruning via Bi-level Optimization
Figure 4 for Advancing Model Pruning via Bi-level Optimization
* Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022) 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Efficient Multi-Prize Lottery Tickets: Enhanced Accuracy, Training, and Inference Speed


Sep 26, 2022
Hao Cheng, Pu Zhao, Yize Li, Xue Lin, James Diffenderfer, Ryan Goldhahn, Bhavya Kailkhura

Add code
Alert button

Figure 1 for Efficient Multi-Prize Lottery Tickets: Enhanced Accuracy, Training, and Inference Speed
Figure 2 for Efficient Multi-Prize Lottery Tickets: Enhanced Accuracy, Training, and Inference Speed
Figure 3 for Efficient Multi-Prize Lottery Tickets: Enhanced Accuracy, Training, and Inference Speed
Figure 4 for Efficient Multi-Prize Lottery Tickets: Enhanced Accuracy, Training, and Inference Speed

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

Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution


Jul 25, 2022
Yushu Wu, Yifan Gong, Pu Zhao, Yanyu Li, Zheng Zhan, Wei Niu, Hao Tang, Minghai Qin, Bin Ren, Yanzhi Wang

Add code
Alert button

Figure 1 for Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution
Figure 2 for Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution
Figure 3 for Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution
Figure 4 for Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution

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

Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization


Jun 02, 2022
Yanyu Li, Pu Zhao, Geng Yuan, Xue Lin, Yanzhi Wang, Xin Chen

Add code
Alert button

Figure 1 for Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization
Figure 2 for Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization
Figure 3 for Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization
Figure 4 for Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization

   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
3
4
>>