About Me

I am currently an Applied Scientist at Microsoft, where I work on RL post-training for OpenAI and Microsoft models. Previously, I was a Research Fellow at MMLab@NTU, working with Prof. Xingang Pan. I received my Ph.D. in June 2024 from the University of Science and Technology of China (USTC), where I was advised by Prof. Nenghai Yu and Prof. Weiming Zhang.

I am deeply grateful to Dr. Dongdong Chen for his continuous guidance and support throughout my academic journey. During my Ph.D., I was also fortunate to receive mentorship from Prof. Jing Liao and Dr. Gang Hua.

My research interests broadly lie in Agentic AI, Computer Vision, and Generative AI, with a particular focus on image and video synthesis and editing. Feel free to email me for collaboration or academic discussion.

News

Experience

Applied Scientist

Microsoft

Apr 2026 - Present

Research Fellow

Nanyang Technological University

July 2024 - Apr 2026

Research Scientist Intern

Microsoft

March 2022 - June 2022

Selected Publications

Towards Geometry-Grounded Dense Semantic Matching with VGGT Priors

Songlin Yang, Tianyi Wei, Yushi Lan, Zeqi Xiao, Anyi Rao, Xingang Pan

European Conference on Computer Vision (ECCV), 2026

Paper Code

From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space

Jiazi Bu, Pengyang Ling, Yujie Zhou, Yibin Wang, Yuhang Zang, Tianyi Wei, Xiaohang Zhan, Jiaqi Wang, Tong Wu, Xingang Pan, Dahua Lin

European Conference on Computer Vision (ECCV), 2026

Paper Project Page

Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning

Weitao Feng, Lixu Wang, Peizhuo Lv, Tianyi Wei, Jie Zhang, Chongyang Gao, Sinong Zhan, Wei Dong

The ACM Conference on Computer and Communications Security (CCS), 2026

Paper Code Project Page

Boosting Monocular Metric Depth Estimation via Bokeh Rendering

Hangwei Zhang, Armando Fortes, Tianyi Wei, Xingang Pan

Proceedings of the 41st International Conference on Machine Learning (ICML), 2026

Paper Code Project Page

Enhancing MMDiT-Based Text-to-Image Models for Similar Subject Generation

Tianyi Wei, Dongdong Chen, Yifan Zhou, Xingang Pan

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026

Paper Code Project Page

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers

Yifan Zhou, Zeqi Xiao, Tianyi Wei, Shuai Yang, Xingang Pan

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

Paper Code

FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing

Tianyi Wei, Yifan Zhou, Dongdong Chen, Xingang Pan

IEEE/CVF International Conference on Computer Vision (ICCV), 2025

Paper Code Project Page

Scale Your Instructions: Enhance the Instruction-Following Fidelity of Unified Image Generation Model by Self-Adaptive Attention Scaling

Chao Zhou, Tianyi Wei, Nenghai Yu

IEEE/CVF International Conference on Computer Vision (ICCV), 2025

Paper Code

Deep Image Matting with Sparse User Interactions

Tianyi Wei, Dongdong Chen, Wenbo Zhou, Jing Liao, Hanqing Zhao, Weiming Zhang, Gang Hua, Nenghai Yu

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024

Paper

AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA

Weitao Feng, Wenbo Zhou, Jiyan He, Jie Zhang, Tianyi Wei, Guanlin Li, Tianwei Zhang, Weiming Zhang, Nenghai Yu

Proceedings of the 41st International Conference on Machine Learning (ICML), 2024

Paper Code

SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Models

Feifei Wang, Zhentao Tan, Tianyi Wei, Yue Wu, Qidong Huang

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Paper Code

A Geometric Distortion Immunized Deep Watermarking Framework with Robustness Generalizability

Linfeng Ma, Han Fang, Tianyi Wei, Zijin Yang, Zehua Ma, Weiming Zhang, Nenghai Yu

European Conference on Computer Vision (ECCV), 2024

Paper

FaceRSA: RSA-Aware Facial Identity Cryptography Framework

Zhongyi Zhang, Tianyi Wei, Wenbo Zhou, Hanqing Zhao, Weiming Zhang, Nenghai Yu

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2024

Paper Code

HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending

Tianyi Wei, Dongdong Chen, Wenbo Zhou, Jing Liao, Weiming Zhang, Gang Hua, Nenghai Yu

IEEE/CVF International Conference on Computer Vision (ICCV), 2023

Paper Code

HairCLIP: Design Your Hair by Text and Reference Image

Tianyi Wei, Dongdong Chen, Wenbo Zhou, Jing Liao, Zhentao Tan, Lu Yuan, Weiming Zhang, Nenghai Yu

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

Paper Code

E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversion

Tianyi Wei, Dongdong Chen, Wenbo Zhou, Jing Liao, Weiming Zhang, Lu Yuan, Gang Hua, Nenghai Yu

IEEE Transactions on Image Processing (TIP), 2022

Paper Code Demo

Multi-Attentional Deepfake Detection

Hanqing Zhao, Wenbo Zhou, Dongdong Chen, Tianyi Wei, Weiming Zhang, Nenghai Yu

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Paper Code

Honors and Awards

Academic Services