pkurainbow Goto Github PK

followers: 518.0 following: 115.0 repos: 278.0 gists: 3.0

Name: Researcher.YuanYuhui

Type: User

Company: SeniorResearcher@MicrosoftResearch

Bio: Keep Calm

Twitter: RainbowYuhui

Location: Beijing

Blog: https://www.microsoft.com/en-us/research/people/yuyua/

Hi there 👋

🔭 Yuhui Yuan is currently a senior researcher at the Visual Computing Group of Microsoft Research Asia. He completed his Ph.D., M.S., and B.S. degrees from the Institute of Computing Technology, CAS, Peking University, and Nanjing University in 2022, 2017, and 2014, respectively. Currently, he is leading efforts on (i) developing generative AI technologies to help ship multiple products to Microsoft Designer and (ii) developing the next-generation graphic design engine for high-quality business content generation (e.g., posters, flyers, infographics, diagram, chart, and slides). His recent representative works include LISA for reasoning segmentation (CVPR’2024), COLE for multi-layered and editable graphic design generation, Glyph-ByT5 for accurate visual text rendering, and SPO for human preference learning of diffusion models.
🔭 He has rich experience in areas such as general visual semantic/instance/panoptic segmentation and object recognition since joining MSRA in 2017. His representative works on segmentation and object detection include OCRNet (ECCV’2020), OCNet (IJCV’2021), and H-DETR (CVPR’2023).
🔭 Please send an email to [email protected] or [email protected] if you are interested in an internship position related to business content creation and editing or multimodal reasoning and planning.

Researcher.YuanYuhui's Projects

1806

18.06 course at MIT

18303

18.303 - Linear PDEs course

18330

18.330 Introduction to Numerical Analysis

18335

18.335 - Introduction to Numerical Methods course

18s191

Course 18.S191 at MIT, Spring 2021 - Introduction to computational thinking with Julia:

2020-instanceseg

Deep Variational Instance Segmentation

3d-machine-learning

A resource repository for 3D machine learning

3detr

Code & Models for 3DETR - an End-to-end transformer model for 3D object detection

3dfuture_ins_seg

1st Place Solutions of 3D AI Challenge 2020(IJCAI-PRICAI 2020 Workshop) - Instance Segmentation Track

7ma7x

ab3dmot

Official Python Implementation for "3D Multi-Object Tracking: A Baseline and New Evaluation Metrics", IROS 2020, ECCVW 2020

absphreak

:octocat: Hello there! This repository is for the welcome message on my Github Profile.

academic-project-page-template

A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

adaptive-segmentation-mask-attack

Pre-trained model, code, and materials from the paper "Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation" (MICCAI 2019).