Hi, I am Junjiao Tian!

I am a Member of Technical Staff at Microsoft AI (MAI) within the Superintelligence team. I earned my PhD from the Robotics Perception and Learning Lab (RIPL) at Georgia Tech, advised by Prof. Zsolt Kira. I also contributed to the Bot Intelligence Group (BIG) at Carnegie Mellon University under Prof. Jean Oh. My research focuses on algorithmic methods to enhance the robustness of deep learning models, multimodal generation, and foundation models.

Google Scholar

Publications

MAI-Image-2

Microsoft AI Superintelligence Team (2026)
Contributed to the development and release of the MAI-Image-2 model.
[Announcement] [Media]

Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models

Neural Information Processing Systems (NeurIPS24)
Junjiao Tian, Chengyue Huang, Zsolt Kira.
[Paper] [Code]

Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion

Conference on Computer Vision and Pattern Recognition (CVPR24)
Junjiao Tian, Lavisha Aggarwal, Andrea Colaco, Zsolt Kira, Mar Gonzalez-Franco.
[Paper] [Project Page] [Code]

Fast Trainable Projection for Robust Fine-tuning

Neural Information Processing Systems (NeurIPS23)
Junjiao Tian, Yen-Cheng Liu, James Seale Smith, Zsolt Kira.
[Paper] [Code]

Trainable Projected Gradient Method for Robust Fine-Tuning

Conference on Computer Vision and Pattern Recognition (CVPR23)
Junjiao Tian, Xiaoliang Dai, Chih-Yao Ma, Zecheng He, Yen-Cheng Liu, Zsolt Kira.
[Paper] [Code]

Striking the Right Balance: Recall Loss for Semantic Segmentation

International Conference on Robotics and Automation (ICRA22)
Junjiao Tian, Niluthpol Mithun, Zach Seymour, Han-Pan Chiu, Zsolt Kira
[Paper] [Code]

A Geometric Perspective towards Neural Calibration via Sensitivity Decomposition

Neural Information Processing Systems (NeurIPS21) (Spotlight < 3%)
Junjiao Tian, Dylan Yung, Yen-Chang Hsu, Zsolt Kira
[Paper] [Code] [Project Page]

Exploring Covariate and Concept Shift for Out-of-Distribution Detection

NeurIPS Workshop on Distribution Shift (NeurIPS21)
Junjiao Tian, Yen-Chang Hsu, Yilin Shen, Hongxia Jin, Zsolt Kira
[Paper] [Project Page]

Posterior Re-calibration for Imbalanced Datasets

Neural Information Processing Systems (NeurIPS20)
Junjiao Tian, Yen-Cheng Liu, Nathan Glaser, Yen-Chang Hsu, Zsolt Kira
[Paper] [Code]

UNO: Uncertainty-aware Noisy-Or Multimodal Fusion for Unanticipated Input Degradation

International Conference on Robotics and Automation (ICRA20)
Junjiao Tian, Wesley Cheung, Nathan Glaser, Yen-Cheng Liu, Zsolt Kira
[Paper] [Code]

Image Captioning with Compositional Neural Module Networks

International Joint Conference on Artificial Intelligence (IJCAI '19)
Junjiao Tian, Jean Oh
[Paper]

Industry Experience

Microsoft AI - Member of Technical Staff, Superintelligence/Multimodal Team (2026 - Present)

Meta GenAI - Research Scientist (2024 - 2026)

Google - AR experiences (2023)

Meta Reality Labs - Mobile Vision Team (2022)

Samsung Research America - AI Center (2021)

SRI International - Center for Vision Technology (2020)

Junjiao Tian