about image

Shanghua Gao

He is currently a Research Fellow at Harvard University, where his work centers on developing foundation models and universal representation learning methods to enhance understanding and interaction with the real world. His research emphasizes general techniques, including AI agents, generative modeling, self-supervised learning, and the design of foundation models. Broadly, his focus is on advancing these models to pursue artificial general intelligence across various fields such as computer vision, biomedical applications, and time series analysis. His projects have gained significant traction, with over 5,000 citations and thousands of GitHub stars, and some have successfully transitioned into real-world products.

My Works
Collect from Shanghua Gao

Selected Works

Google Scholar | Github

Empowering Biomedical Discovery with AI Agents

Shanghua Gao, Ada Fang*, Yepeng Huang*, Valentina Giunchiglia*, Ayush Noori*, Jonathan Richard Schwarz, Yasha Ektefaie, Jovana Kondic, Marinka Zitnik

Cell, 2024

[Cell Press] [arxiv]

UniTS: Building a Unified Time Series Model

Shanghua Gao, Teddy Koker, Owen Queen, Thomas Hartvigsen, Theodoros Tsiligkaridis, Marinka Zitnik

Conference on Neural Information Processing Systems (NeurIPS), 2024

Star [pdf] [code]

Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation

Shanshan Zhong, Zhongzhan Huang, Shanghua Gao, Wushao Wen, Liang Lin, Marinka Zitnik, Pan Zhou

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Star [pdf] [project page] [code]

Masked Diffusion Transformer is a Strong Image Synthesizer

Shanghua Gao, Pan Zhou, Ming-Ming Cheng, Shuicheng Yan

IEEE International Conference on Computer Vision (ICCV), 2023

Star [pdf] [code]

Editanything: Empowering unparalleled flexibility in image editing and generation

Shanghua Gao, Zhijie Lin, Xingyu Xie, Pan Zhou, Ming-Ming Cheng, Shuicheng Yan

Proceedings of the 31st ACM International Conference on Multimedia, 2023

Star [pdf] [code]

Large-scale Unsupervised Semantic Segmentation

Shanghua Gao, Zhong-Yu Li, Ming-Hsuan Yang, Ming-Ming Cheng, Junwei Han, Philip Torr

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023

Star [pdf] [project] [code] [ImageNet-S]

Towards Sustainable Self-supervised Learning

Shanghua Gao, Pan Zhou, Ming-Ming Cheng, Shuicheng Yan

Tech report, 2022

[pdf] [code]

RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks

Shanghua Gao, Zhong-Yu Li, Qi Han, Ming-Ming Cheng, Liang Wang

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022

Global2Local: Efficient Structure Search for Video Action Segmentation

Shanghua Gao*, Qi Han*, Zhong-Yu Li, Pai Peng, Liang Wang, Ming-Ming Cheng

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Star [pdf-pami] [pdf-cvpr] [project] [code]

A Highly Efficient Model to Study the Semantics of Salient Object Detection

Ming-Ming Cheng*, Shanghua Gao*, Ali Borji, Yong-Qiang Tan, Zheng Lin, Meng Wang

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021

Highly Efficient Salient Object Detection with 100K Parameters

Shanghua Gao, Yong-Qiang Tan, Ming-Ming Cheng, Chengze Lu, Yunpeng Chen, Shuicheng Yan

European Conference on Computer Vision (ECCV), 2020

Star [pdf-pami] [pdf-eccv] [bib] [project] [code]

Representative Batch Normalization with Feature Calibration

Shanghua Gao, Qi Han, Duo Li, Ming-Ming Cheng, Pai Peng

Oral, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Star [pdf] [project] [bib] [code]

Res2Net: A New Multi-scale Backbone Architecture

Shanghua Gao, Ming-Ming Cheng, Kai Zhao, Xin-Yu Zhang, Ming-Hsuan Yang, Philip Torr

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021

Star [pdf] [bib] [DEMO] [project] [code] [PPT] [中文版]

JCS: An explainable COVID-19 diagnosis system by joint classification and segmentation

Yu-Huan Wu, Shanghua Gao, Jie Mei, Jun Xu, Deng-Ping Fan, Chao-Wei Zhao, Ming-Ming Cheng

IEEE Transactions on Image Processing (TIP), 2021

[pdf] [bib]

Point-based Iterative Graph Exploration for Road Graphs Extraction

Yong-Qiang Tan, Shanghua Gao, Xuan-Yi Li, Ming-Ming Cheng, Bo Ren

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020

[pdf] [bib] [project]

Optimizing the F-measure for Threshold-free Salient Object Detection

Kai Zhao, Shanghua Gao, Wenguan Wang, Ming-Ming Cheng

IEEE International Conference on Computer Vision (ICCV), 2019

[pdf] [bib] [project] [code]

Hi-Fi: Hierarchical Feature Integration for Skeleton Detection

Kai Zhao, Wei Shen, Shanghua Gao, Dandan Li, Ming-Ming Cheng

International Joint Conference on Artificial Intelligence (IJCAI), 2018

[pdf] [bib] [project] [code] [中文版]

Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground

Deng-Ping Fan, Ming-Ming Cheng*, Jiang-Jiang Liu, Shanghua Gao, Qinbin Hou, Ali Borji

European Conference on Computer Vision (ECCV), 2018

[pdf] [bib] [project] [中文版]

Orbital Angular Momentum for Wireless Communications

Wenchi Cheng, Wei Zhang, Haiyue Jing, Shanghua Gao, Hailin Zhang

IEEE Wireless Communications Magazine, 2018

[pdf] [bib] [project]

Bifocal-Lens Converging Based OAM Wireless Communications

Shanghua Gao, Wenchi Cheng, Hailin Zhang

IEEE Journal of Communications and Information Networks (JCIN), 2019

High-efficient beam-converging for UCA based radio vortex wireless communications

Shanghua Gao, Wenchi Cheng, Hailin Zhang, Zan Li

IEEE/CIC International Conference on Communications in China (ICCC), 2017

[pdf_journal] [pdf_conf] [bib_journal] [bib_conf] [project]

Contact

  • Email shanghuagao@gmail.com
  • Addr Department of Biomedical Informatics, Harvard Medical School, Boston, MA 02115, USA.
  • Hosted by Github