Yanzhi Tian (田炎智), is currently a PhD student at School of Computer Science and Technology, Beijing Institute of Technology(北京理工大学计算机学院). He received his bachelor’s degree from XUTELI School, Beijing Institute of Technology(北京理工大学徐特立英才班) in 2023, majoring in computer science.
His research interests include Machine Translation and Large Language Models.
🔥 News
- 2025.08: 🎉🎉 1 paper has been accepted by EMNLP 2025 Main!
- 2025.05: 🎉🎉 1 paper has been accepted by ACL 2025 Findings!
📝 Publications
PRIM: Towards Practical In-Image Multilingual Machine Translation
Yanzhi Tian, Zeming Liu, Zhengyang Liu, Chong Feng, Xin Li, Heyan Huang, Yuhang Guo
-
We propose PRIM, the first real-world multilingual In-Image Machine Translation benchmark, and develop VisTrans, an end-to-end model that achieves superior translation quality and visual effect.
-
Exploring In-Image Machine Translation with Real-World Background
Yanzhi Tian, Zeming Liu, Zhengyang Liu, Yuhang Guo
- We tackle In-Image Machine Translation with real-world backgrounds by introducing a new dataset IIMT30k and the DebackX model for better translation and visual quality.
In-Image Neural Machine Translation with Segmented Pixel Sequence-to-Sequence Model
Yanzhi Tian, Xiang Li, Zeming Liu, Yuhang Guo, Bin Wang
- We design an end-to-end model for IIMT that outperforms traditional cascade methods for the first time.
📖 Educations
- 2023.09 - now: PhD Student. Computer Science, School of Computer Science and Technology, Beijing Institute of Technology.
- 2019.09 - 2023.06: Undergraduate. Computer Science, XUTELI School, Beijing Institute of Technology.
💻 Internships
- 2025.06 - now, Internship at Zhipu AI. Mentor: Cunxiang Wang.
- 2023.01 - 2023.06, Internship at Xiaomi AI Lab. Mentor: Xiang Li.