Yujia Chen (陈禹嘉)

I'm a Senior Machine Learning Engineer in Google Reseach, my current focus lies in applied research for real-time, on-device technologies in the fields of Computer Vision and Machine Learning. My expertise encompasses scene understanding, deep generative modeling, and representation learning. Before joining Google, I was an Applied Scientist at Amazon, where I developed innovative RGB-only computer vision algorithms for a range of products. This role followed my graduation from the MSCV program at Carnegie Mellon University's Robotics Institute, under the guidance of Prof. David Held and Kris Kitani.

My passion is in transitioning AI technology from academic theory to practical, real-world applications. Recently, I mainly focus on Generative AI, scene understanding and the development of advanced vision technologies for mobile devices, including the Face Unlock feature on Google's Pixel 8a, 9 & 9 Pro & XL & Fold (Made by Google '24), Pixel 8 and 8 Pro (Made by Google '23), Pixel Fold & 7a (Google I/O'23), Pixel 7 & 7 Pro (RGB-based, Made by Google '22). Before Google, I was part of a research team at Amazon, contributing to the development of vision-only technologies for the pioneering Just-Walk-Out (JWO) grocery store, also known as Amazon Go. Additionally, I have made significant contributions to Amazon Prime Video's Video Compliance System and the Virtual Product Placement feature, both of which are utilized globally.

News

• [2025/03]  One papers accepted at CVPR 2025.
• [2025/02]  Two papers accepted at ICLR 2025, including one oral presentation!
• [2024/11]  Selected as a NeurIPS 2024 Top Reviewer.
• [2024/09]  GOT A YES IN PARIS! 💍
• [2024/02]  One paper accepted at CVPR 2024.
• [2022/06]  Joined Google Research as a Machine Learning Engineer in Seattle.
• [2021/06]  Joined Amazon Prime Video to work on the video compliance system and virtual product placement (VPP).
• [2020/01]  Started a new adventure as an Applied Scientist at Amazon in downtown Seattle!
• [2019/09]  Served as a Teaching Assistant for Introduction to Machine Learning (10601) at CMU, instructed by Prof. Matt Gormley.
• [2019/05]  Started an amazing journey at Amazon as an Applied Scientist Intern, working on scene understanding and customer association.
• [2018/12]  Worked as a Graduate Assistant under Prof. David Held, focusing on deep slope estimation and cloth part detection.
• [2017/05]  Interned at the National Laboratory of Pattern Recognition, Chinese Academy of Sciences, advised by Prof. Ran He.

Publications

• SEAL: Semantic Attention Learning for Long Video Representation
  Lan Wang, Yujia Chen, Du Tran, Vishnu Boddeti, and Wen-Sheng Chu
  (CVPR'25) Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
  [Project page]
• OOD Learner via In-Context Learning
  Ziqian Lin, Yaojie Liu, Runze Li, Yujia Chen, Yixuan Li, and Wen-Sheng Chu
  [Project page]
• Semantic Image Inversion and Editing using Stochastic Rectified Differential Equations
  Litu Rout, Yujia Chen, Nataniel Ruiz, Constantine Caramanis, Sanjay Shakkottai, and Wen-Sheng Chu
  (ICLR'25) The Thirteenth International Conference on Learning Representations
  [Project page]
• RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control (Oral)
  Litu Rout, Yujia Chen, Nataniel Ruiz, Constantine Caramanis, Sanjay Shakkottai, and Wen-Sheng Chu
  (ICLR'25) The Thirteenth International Conference on Learning Representations
  [Project page]
• Beyond First-order Tweedie: Solving Inverse Problems using Latent Diffusion
  Litu Rout, Yujia Chen, Abhishek Kumar, Constantine Caramanis, Sanjay Shakkottai, and Wen-Sheng Chu
  (CVPR'24) Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
  [Project page]
• Adversarial Occlusion-aware Face Detection (Oral)
  Yujia Chen, Lingxiao Song, Ran He
  (BTAS'18) International Conference on Biometrics Theory, Applications and Systems 2018
• GM-Net: Learning Features with More Efficiency (Oral)
  Yujia Chen, Ce Li
  (ACPR'17) Asian Conference on Pattern Recognition 2017

Community Service

I serve as the conference reviewer for CVPR, ICLR, AISTATS, ACCV, NeurIPS (25' Top reviewer), ICML, ICCV, SIGGRAPH, TMLR.

Life

I do basketball and boxing. I have "twocatsandadog" (yes, that's my Wi-Fi password). The biggest boy cat, Noodle, only comes back home for food and sleep, and spends the rest of his life playing with the squirrels and birds in the wild. The sister cat, Pudding, is a little princess sleeping on the sofa all day. And the little brother, JoJo, is the famous White Golden Retriever in the neighborhood who likes to scramble in the mud!