2025.02.22 - 🧬 Another speech on the Nüwa foundation models was given at the 2025 Global Developer Conference. This presentation discussed some recent thoughts on "Virtual Cell" or "Life Simulator", which was under development at SAIS.
2025.02.03 - 🌧 I recently received several inquiries about my previous projects. The details are:
2025.01.11 - 🌏 I delivered a speech on the Nüwa foundation models at the 4th Guanghua Forum. This presentation highlighted a recent accomplishment we've achieved at SAIS.
I currently hold the position of Senior Research Fellow at the Shanghai Academy of Artificial Intelligence for Science (SAIS). My work at SAIS focuses on leveraging Artificial Intelligence to advance Life Science, particularly in the area of Multiomics & Multimodal Foundation Models and their clinical applications. This role builds upon my extensive experience at Ant & Alibaba Group, where I specialized in Computer Vision and Vision Foundation Model.
Previously, I conducted applied research at Ant & Alibaba Group. Over the course of my 8+ years there, I applied my expertise in digital signal processing, computer vision, and multimodal perception to develop innovative and award-winning AI products, such as 定损宝 (recipient of the Shenzhen 2018 Fintech Award) and 亿亩田 (recipient of the CCF 2022 Technology Advancing Award). Additionally, I was an executive member of the Wuhan University - Ant Group United Laboratory, where I collaborated with leading researchers and engineers to develop SkySense, a cutting-edge vision foundation model for remote sensing imagery.
I hold a Master's degree in Communication Systems from the Swiss Federal Institute of Technology in Lausanne (EPFL) and a Bachelor's degree with honors from Zhejiang University, majoring in Information and Communication Engineering. My professional journey in both large corporation and innovative start-up across Europe (i.e. Sony and Tractable Ltd) has afforded me valuable experience.
My current research interests encompass Multiomics Foundation Model, Computer Vision, and Multimodal Perception. I have published 10+ papers and served as a reviewer for 5+ prestigious conferences and journals. I hold 10+ international patents, issued by patent offices in Europe, the United States, Japan, Korea, Singapore, and other countries worldwide. I am deeply passionate about solving challenging problems and creating impactful solutions that might benefit the whole world.
- NasalSeg: A Dataset for Automatic Segmentation of Nasal Cavity and Paranasal Sinuses from 3D CT Images
Yichi Zhang, Jing Wang, Tan Pan, Quanling Jiang, Jingjie Ge, Xin Guo, Chen Jiang, Jie Lu, Jianning Zhang, Xueling Liu, Mei Tian, Yuan Qi, Yuan Cheng, Chuantao Zuo
Scientific Data, 2024
- Simultaneously Short- and Long-Term Temporal Modeling for Semi-Supervised Video Semantic Segmentation
Jiangwei Lao, Weixiang Hong, Xin Guo, Yingying Zhang, Jian Wang, Jingdong Chen, Wei Chu
CVPR 2023
- SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery
Xin Guo*, Jiangwei Lao*, Bo Dang*, Yingying Zhang, Lei Yu, Lixiang Ru, Liheng Zhong, Ziyuan Huang, Kang Wu, Dingxiang Hu, Huimei He, Jian Wang, Jingdong Chen, Ming Yang, Yongjun Zhang, Yansheng Li
CVPR 2024
- POA: Pre-training Once for Models of All Sizes
Yingying Zhang, Xin Guo, Jiangwei Lao, Lei Yu, Lixiang Ru, Jian Wang, Guo Ye, Huimei He, Jingdong Chen, Ming Yang
ECCV 2024
- Parameter-Efficient Complementary Expert Learning for Long-Tailed Visual Recognition
Lixiang Ru, Xin Guo, Lei Yu, Yingying Zhang, Jiangwei Lao, Jian Wang, Jingdong Chen, Yansheng Li, Ming Yang
ACM Multimedia 2024
- Unleashing the potential of remote sensing foundation models via bridging data and computility islands
Yansheng Li, Jieyi Tan, Bo Dang, Mang Ye, Sergey A Bartalev, Shinkarenko Stanislav, Linlin Wang, Yingying Zhang, Lixiang Ru, Xin Guo, Liangqi Yuan, Lei Yu, Jingdong Chen, Ming Yang, José Marcato Junior, Yongjun Zhang
The Innovation, 2025
- Automatic Car Damage Assessment System: Reading and Understanding Videos as Professional Insurance Inspectors
Wei Zhang, Yuan Cheng, Xin Guo, Qingpei Guo, Jian Wang, Qing Wang, Chen Jiang, Meng Wang, Furong Xu, Wei Chu
AAAI 2020
- Towards Efficient Pre-Trained Language Model via Feature Correlation Distillation
Kun Huang, Xin Guo, Meng Wang
NeurIPS 2023
- NMF-based blind source separation using a linear predictive coding error clustering criterion
Xin Guo, Stefan Uhlich, Yuki Mitsufuji
ICASSP 2015
1. EP3201917B1: Xin Guo, Stefan Uhlich, Yuhki Mitsufuji, Method, apparatus and system for blind source separation
2. US10943126B2: Xin Guo, Yuan Cheng, Chen Jiang, Method and apparatus for processing video stream
3. US11216690B2: Xin Guo, Yuan Cheng, Jun Huang, System and method for performing image processing based on a damage assessment image judgement model
4. SG11202011405YA: Xin Guo, Yuan Cheng, Chen Jiang, Zhihong Lu, Image processing method and apparatus
5. US11049334B2: Haitao Zhang, Juan Xu, Jinlong Hou, Jian Wang, Xin Guo, Danni Cheng, Yue Hu, Bokun Wu, Yanqing Chen, Picture-based vehicle loss assessment
6. US010846556B2: Jinlong Hou, Haitao Zhang, Xin Guo, Juan Xu, Jian Wang, Yuan Cheng, Danni Cheng, Vehicle insurance image processing method, apparatus, server, and system
7. US11151384B2: Haitao Zhang, Jinlong Hou, Xin Guo, Yuan Cheng, Jian Wang, Juan Xu, Fan Zhou, Kan Zhang, Method and apparatus for obtaining vehicle loss assessment image, server and terminal device
8. US10817956B2: Haitao Zhang, Juan Xu, Jinlong Hou, Jian Wang, Xin Guo, Danni Cheng, Yue Hu, Bokun Wu, Yanqing Chen, Image-based vehicle damage determining method and apparatus, and electronic device
9. KR102418446B1: Haitao Zhang, Juan Xu, Jinlong Hou, Jian Wang, Xin Guo, Danni Cheng, Yue Hu, Bokun Wu, Yanqing Chen, Picture-based vehicle damage assessment method and apparatus, and electronic device
10. JP6905081B2: Haitao Zhang, Jinlong Hou, Xin Guo, Yuan Cheng, Jian Wang, Juan Xu, Fan Zhou, Kan Zhang, Methods and Devices for Obtaining Vehicle Loss Assessment Images and Devices, Servers, and Terminal Devices
1. Teaching Assistant: Pattern Classification and Machining Learning (2013)
Swiss Federal Institute of Technology in Lausanne (EPFL), Prof. Matthias Seeger
2. Reviewer Service: CVPR, ICLR, NeurIPS, KDD, ACM Multimedia, ICME, ICPR, TGRS
1. Dingsunbao: An Automatic Car Damage Assessment System
Radio Television Suisse in 2018, from 2:21:09 to 2:22:12
2. Dingsunbao: AI-based Car Damage Assessment System
Alipay-NUS Enterprise Social Innovation Challenge(ANSIC) in 2018, Malaysia
1. KDD CUP 2022 - Amazon ESCI Challenge
Ranked 16th@Task1 and 13th@Task2, among 1699 participants
2. ATEC 2022 - Remote Sensing Track
Co-organizer of the competition and the corresponding Bilibili show
3. 2024 ISPRS TC I Contest on Intelligent Interpretation for Multi-modal Remote Sensing Application
Ranked 6th@Task2 and 5th@Task3, among 302 participants
4. 2024 The 2nd World AI4S Prize - Life Science Track
Co-organizer of the competition
2008: TOSHIBA Scholarship (Donated by Toshiba, awards 25 undergraduates each year in China)
2008-2012: Scholarship for Outstanding Students by Zhejiang University
2010: Scholarship for National Talents Program
2012: Outstanding Graduates by Zhejiang University (Graduated with honors)
2015: IEEE Signal Processing Society Travel Grant
2020: Alibaba Chengdian Annual Philanthropy Award
2023: Ant Group T-Star Award (Top 10 Innovations among Ant Group's all tech projects from 2022)
Please contact me for CV.
With the development of modern LLMs (i.e. Large Languege Models), we’ve reached the turning point that the carefully trained model is more knowledgeable than most human-beings to some extent. The emergance of ChatGPT and recently published GPT4.0 sheds light on building Artificial General Intelligence in a feasible way 
In this blog, I would like to briefly introduce GPT-series and discuss its current limitations...
Senior Research Fellow
@ SAIS
Senior R&D Engineer
@ Ant & Alibaba Group
Master Degree @ EPFL
Research Intern @ Sony
Data Scientist @ Tractable
Bachelor Degree
@ Zhejiang University
