Junjiao Tian
Junjiao

Hi, I am Junjiao Tian!

I am a Member of Technical Staff at Microsoft AI (MAI) working in the Multimodal 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.

Image Google Scholar
```
Image

Ph.D. Student in Robotics
Georgia Tech
Aug 2019 - Aug 2024

Image

M.S. in Robotics
CMU
Sep 2017 - May 2019

Image

B.S. in ECE
B.S. in MechSE
UIUC
Sep 2013 - May 2017

Projects

MAI-Image-2

MAI-Image-2

Microsoft AI Superintelligence Team (2026)
Core contributor to the development and release of MAI-Image-2, a text-to-image model for high-quality image generation.
[Announcement] [Media]
MAI-Image-2.5

MAI-Image-2.5

Microsoft AI Superintelligence Team (2026)
Core contributor to MAI-Image-2.5, which adds editing capabilities and ranked #2 on Lmarena.
[Model Page]

Publications

Image

Think in Strokes, Not Pixels: Process-driven Image Generation via Interleaved Reasoning

European Conference on Computer Vision (ECCV2026)
Lei Zhang, Junjiao Tian, Zhipeng Fan, Kunpeng Li, Jialiang Wang, Weifeng Chen, Markos Georgopoulos, Felix Juefei-Xu, Julian McAuley, Manling Li, Zecheng He.
[Paper] [Reference]
Image

Directional Gradient Projection for Robust Fine-tuning of Foundation Models

International Conference on Learning Representations (ICLR25)
Chengyue Huang, Junjiao Tian, Brisa Maneechotesuwan, Shivang Chopra, Zsolt Kira.
[Paper] [Reference]
Image

Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models

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

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]
Image

Fast Trainable Projection for Robust Fine-tuning

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

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]
Image

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]
Image

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]
Image

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]
Image

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]
Image

When2com: Multi-Agent Perception via Communication Graph Grouping

IEEE Conference on Computer Vision and Pattern Recognition (CVPR20)
Yen-Cheng Liu, Junjiao Tian*, Nathaniel Glaser*, Zsolt Kira (* indicates equal contribution)
[Paper][Project Page]
Image

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

Who2com: Collaborative Perception via Learnable Handshake Communication

International Conference on Robotics and Automation (ICRA20)
Yen-Cheng Liu, Junjiao Tian, Chih-Yao Ma, Nathaniel Glaser, Chia-Wen Kuo, Zsolt Kira
[Paper][Project Page]
Image

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)

Extracurricular

Academics Vice President of RoboGrads at Georgia Tech (Fall 2020 - Spring 2021).