Yunjie Tian · 田运杰

Postdoctoral Associate, University at Buffalo

Computer Vision Multimodal Learning Representation Learning Real‑time Detection

I will be joining TikTok as a Senior Research Scientist. I am currently working with Prof. David Doermann at UB. I received my Ph.D. from LAMP, UCAS in 2024, advised by Prof. Qixiang Ye. B.E. from Jilin University (2019).

Research Focus

My research spans vision foundation models, multimodal LLMs, and efficient real‑time perception. I design architectures and training strategies that make models faster, simpler, and clearer for visual and multimodal signals.

Selected Publications

Yunjie Tian, Qixiang Ye, David Doermann

YOLOv12: Attention‑Centric Real‑Time Object Detectors

Arxiv 2025

Paper Code

Xi Tang, Jihao Qiu, Lingxi Xie, Yunjie Tian, Jianbin Jiao, Qixiang Ye

Adaptive Keyframe Sampling for Long Video Understanding

CVPR 2025

Paper Code

Jihao Qiu, Yuan Zhang, Xi Tang, Lingxi Xie, Tianren Ma, Pengyu Yan, David Doermann, Qixiang Ye, Yunjie Tian

Artemis: Towards Referential Understanding in Complex Videos

NeurIPS 2024

Paper Code

Zhaozhi Wang, Yue Liu, Yunfan Liu, Hongtian Yu, Yaowei Wang, Qixiang Ye, Yunjie Tian

vHeat: Building Vision Models upon Heat Conduction

CVPR 2025

Paper Code

Tianren Ma, Lingxi Xie, Yunjie Tian, Boyu Yang, Qixiang Ye

ClawMachine: Fetching Visual Tokens as an Entity for Referring and Grounding

ICLR 2025

Paper Code

Yunjie Tian, Tianren Ma, Lingxi Xie, Qixiang Ye

ChatterBox: Multi‑round Multimodal Referring and Grounding

AAAI 2025

Paper Code

Yunjie Tian, Lingxi Xie, Mengnan Shi, Jiemin Fang, Xiaopeng Zhang, Jianbin Jiao, Qi Tian, Qixiang Ye

Beyond Masking: Demystifying Token‑Based Pre‑Training for Vision Transformers

Pattern Recognition 2025

Paper Code

Yue Liu, Yunjie Tian, Yuzhong Zhao, Hongtian Yu, Lingxi Xie, Yaowei Wang, Qixiang Ye, Yunfan Liu

VMamba: Visual State Space Model

NeurIPS 2024

Paper Code

Yunjie Tian, Lingxi Xie, Jihao Qiu, Jianbin Jiao, Qi Tian, Qixiang Ye

Fast‑iTPN: Integrally Pre‑Trained Transformer Pyramid Network with Token Migration

TPAMI 2024

Paper Code

Yunjie Tian, Lingxi Xie, Jiemin Fang, Jianbin Jiao, Qixiang Ye, Qi Tian

Exploring Complicated Search Spaces with Interleaving‑Free Sampling

TNNLS 2024

Paper

*Hongtian Yu, *Yunjie Tian, Qixiang Ye, Yunfan Liu

Spatial Transform Decoupling for Oriented Object Detection

AAAI 2024

Paper Code

Yunjie Tian, Lingxi Xie, Zhaozhi Wang, Longhui Wei, Xiaopeng Zhang, Jianbin Jiao, Qi Tian, Qixiang Ye

Integrally Pre‑Trained Transformer Pyramid Networks

CVPR 2023

Paper Presentation Code

*Xiaosong Zhang, *Yunjie Tian, Wei Huang, Lingxi Xie, Qi Dai, Qixiang Ye, Qi Tian

HiViT: A Simpler and More Efficient Design of Hierarchical Vision Transformer

ICLR 2023

Paper Code arXiv

Weixi Zhao, Weiqiang Wang, Yunjie Tian

GraFormer: Graph‑Oriented Transformer for 3D Pose Estimation

CVPR 2022

Paper Code

Yunjie Tian, Chang Liu, Lingxi Xie, Qixiang Ye

Discretization‑Aware Architecture Search

Pattern Recognition 2021

Paper Code

*Chang Liu, *Yunjie Tian, Zhiwen Chen, Jianbin Jiao, Qixiang Ye

Adaptive Linear Span Network for Object Skeleton Detection

TIP 2021

Paper Code

Contact

Room 301B, Davis Hall
Department of Computer Science and Engineering
University at Buffalo, SUNY
Buffalo, NY 14260, USA

Email: tianyunjie96@gmail.com