Skip to content
View lyuwenyu's full-sized avatar
👀
👀
190 followers · 0 following
  • Harbin Institute of Technology
  • Beijing, China

Achievements

Achievement: Pair ExtraordinaireAchievement: Starstruckx3Achievement: QuickdrawAchievement: Pull Sharkx3Achievement: Arctic Code Vault Contributor

Achievements

Achievement: Pair ExtraordinaireAchievement: Starstruckx3Achievement: QuickdrawAchievement: Pull Sharkx3Achievement: Arctic Code Vault Contributor

Block or report lyuwenyu

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
lyuwenyu/README.md

👋 Hi there

I am an AI Researcher at Baidu Inc. which I joined in 2021. My research interest covers a wide range of topics in computer vision and multimodal large language model. My publications have over 1,600 citations (as of Dec. 2024).

My works on visual object detection include RTDETR, RTDETRv2, PP-YOLOE, PP-YOLOE+, PP-YOLOE-SOD, PP-PicoDet and PP-YOLOv2. The best known model RTDETR has been integrated into huggingface/transformers and ultralytics/ultralytics repositories. I also have some works on multimodal large language model including PP-InsCapTagger, PP-InfinityDocData and PP-DocBee for data analysis, data generation, and document image understanding. I am also a contributor of several prestigious communities, including pytorch and PaddlePaddle.

Before joining Baidu Inc., I was a Software Engineer at Microsoft from 2019 to 2021, and a Research Intern at Microsoft Research Asia (MSRA) from 2016 to 2017. I received my M.S. degree from Harbin Institute of Technology in 2018.

🔭 Google scholar

📬 Reach out to me: lyuwenyu@foxmail.com

Pinned Loading

  1. RT-DETR Public

    [CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

    Python 3.4k 403

  2. PP-InsCapTagger Public

    Instance Capability Tagger(InsCapTagger) is a multimodal data capability tagging model. 多模态数据能力标签模型，可用于图文数据分析和处理（e.g. 基于信息密度的数据过滤方案、基于模型能力的数据配比方案）。 🔥 🔥 🔥

    8

  3. PaddlePaddle/PaddleDetection Public

    Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

    Python 13.3k 2.9k

  4. PaddlePaddle/PaddleMIX Public

    Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high …

    Python 603 193

759 contributions in the last year

Contribution Graph
Day of Week April May June July August September October November December January February March
Sunday
Monday
Tuesday
Wednesday
Thursday
Friday
Saturday
Learn how we count contributions
Less
No contributions.
Low contributions.
Medium-low contributions.
Medium-high contributions.
High contributions.
More

Contribution activity

March 2025

Created 7 commits in 3 repositories
Created 1 repository

Created a pull request in PaddlePaddle/PaddleMIX that received 1 comment

add cite

+13 −1 lines changed • 1 comment
Opened 2 other pull requests in 1 repository
PaddlePaddle/PaddleMIX 2 merged
Reviewed 13 pull requests in 2 repositories
  • Fix typos
    This contribution was made on Mar 13
12 contributions in private repositories Mar 3 – Mar 28
Loading