Hi! Here is Yuanjun Chai 柴源君 (sounds like Y-wen Joon, Ch-eye), aka Allen. Now I am a MSEE student in University of Washington Seattle
(Go Husky!).
I graduated with highest honors from Xidian University, earning a bachelor’s degree. My thesis about image inpainting received invaluable support by Chao Dong from SIAT-CAS 
. Also, I am so lucky to have the privilege of collaborating with Chao Dong and Yu Qiao from CAS 
working on image&video super-resolution, Jason Cheung from HKU 
working on AI healthcare, Yue Gao from Tsinghua University 
working on Vision.
Previously, I worked a machine learning engineer over 3 years at IT companies, such as VMware AI Lab 
, focusing on LLM, agent and RAG. Before this, I worked in YeahMobi – affiliation of Alibaba Group 
, as a machine learning scientist. I was responsible for the all technical development of AIGC platform Kreado AI 
, including Video creation, virtual avatar, and etc.
Research Interests:
- Computer Vision: low&high level vision, 3D vision, Vision-Language Model (VLM)
- NLP: Language Model agent, RAG, LLM diversity
- Embodiment: sim2real, diffusion policy, Vision-Language Action Model (VLA)
Not only diving into research, I am also willing to empower new technologies into products to make people’s lives better. Thus, I co-founded a start-up INGREM inc, to help high-paraplegia disabled people using computer with precise eyes controling platform.
🔥 News
- 2025.06: 🔥🔥 Our paper DiffPure-VLM about Vision-Language Model Safeguarding has been accepted by ICCV25! See you in Hawaii! 🏖️
- 2024.09: 🥰🥰 Go to University of Washington! I am so excited to start my research new journey in UW!
- 2022.07: 🎉🎉 Thrilled to join VMware as MLE! We do some interesting projects on own LLM platform like h2oGPT (⭐️8k+).
- 2021.03: 👏👏 Rank 10 / 60 in NTIRE 2021 Challenge on Image Deblurring in CVPR 2021 and our method Visual Token Transformer for Image Restoration is selected to present in the summary paper.
- 2021.01: 🥰🥰 Our eyes control platform has helped high-paraplegia disabled people more than 300!
- 2020.08: 🎉🎉 Our IKC – CVPR project about real-world super-resolution get more than ⭐️200+.
📝 Research
Jiawei Wang*, Yushen Zuo*, Yuanjun Chai, Zhendong Liu, Yicheng Fu, Yichun Feng, Kin-Man Lam
Project | 
- Our Robust-VLGuard dataset and DiffPure-VLM defense framework tackle the vulnerability of visual language models (VLMs) to adversarial perturbation attacks. By combining Gaussian noise enhancement and diffusion model-based adversarial noise conversion, we demonstrably improve VLM robustness, even against strong attacks.
IKC: Blind Super-Resolution With Iterative Kernel Correction
Jinjin Gu, Hannan Lu, Wangmeng Zuo, Chao Dong
Project | 
- Our innovative Iterative Kernel Correction (IKC) method tackles blind super-resolution by leveraging characteristic artifacts from kernel mismatch to refine blur kernel estimations. This, combined with our SFTMD network architecture utilizing spatial feature transform layers, delivers enhanced performance across various blur conditions. The code implementation is available on my GitHub.
NTIRE 2021 Challenge on Image Deblurring
Seungjun Nah, Sanghyun Son, Suyoung Lee, Radu Timofte, Kyoung Mu Lee, Yushen Zuo, Yuanjun Chai et al.
- We propose new method Visual Token Transformer for Image Restoration for image deblurring at NTIRE 2021 Challenge on Image Deblurring, which achieves the top 10 place in the leaderboard.
🖥️ Industrial Experience
🧑🎨 AIGC (Generative Model)
Kreado AI: AIGC Platform for Marketing Content Generation
Yuanjun Chai and YeahMobi.inc
- We propose a new AIGC platform for marketing content generation, named Kreado AI. Kreado AI is a hybrid worldwide AIGC platform that combines the strengths of so many AIGC functions:
- Virtual Avatar (talking-face generation, speech synthesis, LLM)
- AI model (text-to-image, LoRA, control net)
- Custom clone serivces (image-to-video, voice clone)
- Here I mainly focus on the Virtual Avatar and AI model algorithms improvement, as well as collaborate with system architect for entire architecture improvement. Users radiate to Europe, Africa, Southeast Asia, and the Americas, with quarterly revenue exceeding US$1 million.
🧙♂️ RAG-based LLM
h2o GPT: AIGC Platform for Marketing Content Generation
Yuanjun Chai
Project | 
- We develop a new RAG-based LLM platform for AI cloud native and private AI. The platform could leverage diverse LLMs with extended dataset such as pdf, code base, dataset and internet links. Here I am responsible for all RAG-based LLM algorithm development, as well as industrial deployment. Functionality includes:
- text QA and chat with RAG
- multi-modal QA and chat
- AI agent
- Next step we would take research about Multi-modal LLM for AI cloud native.
👨⚕️ AI healthcare & Charity
Face Control: Fine Facial Control Platform for High-paraplegia Disabled People
Yuanjun Chai, Ingrem.inc
- I co-founded a start-up Ingrem, with other hardcore guys. We aim to build up a entire bed for living and playing of high-paraplegia disabled people. Here, I am responsible for the development of the software – eyes&facial control platform. Based on computer vision algorithms, the system could help the diabled use their face details (such as eyebrow, eye, mouth, etc.) to control mouse and keyborad elaborately. Thus, our platform and our bed entirely enhance the accessibility of normal computer usage and social networks. We do believe tech make people’s lives better, and we do it!
🎖 Honors and Awards
- 2021.04 Obtain a fully-funded PhD return offer from Li Ka Shing Faculty of Medicine, University of Hong Kong.
- 2019.06 Outstanding Undergraduate Student Award.
- 2019.06 Outstanding Undergraduate Thesis Award (10/5000), Topic: Image Inpainting Based on Deep Learning.
- 2018.08 Cambridge Summer AI Academic Programme Excellent Student – All A+ of Artificial Intelligence Classes.
- 2017.05 Golden Medal of National Computer Design Contest – Birdsong Recognition with Machine Learning.
🎓 Educations
- 2015.08 - 2019.06, Undergraduate, Xidian University.
- 2018.08 - 2018.09, Summer School, University of Cambridge (with Prof. Pietro Lio).
- 2012.08 - 2015.06, High School Affiliated to Northwestern University
🧑💻 Professional Experience
- 2022.07 - 2024.09, Senior Machine Learning Engineer, VMware AI Lab
- 2021.07 - 2022.07, Senior Machine Learning Scientist, YeahMobi – Alibaba Group.
- 2019.05 - 2022.07, Research Assistant in CAS, Tsinghua University and HKU (get return PhD offer).
🏃♂️ Hobbies
My hobbies include Fencing🤺, Basketball🏀, Swimming🏊, Guitar🎸 and Motorcycle🏍️. In the high school, I get my first gold medal in Fencing🤺 at the National Province Games🏅.
Besides, I have my lovely cats🐱:
