🧑 About Me

I am a third-year undergraduate student at Tongji University, affiliated with the School of Ocean and Earth Science and the School of Computer Science and Technology. I major in Marine Technology with a minor in Computer Science and Technology.

My research interests lie in multimodal learning, visual generation, and efficient learning for large-scale models. If you are seeking any form of academic collaboration, please feel free to contact me via email at jingyi_liu@tongji.edu.cn.

Open-source projects can be found on my GitHub, and a full list of my publications is available on Google Scholar.

In my spare time, I enjoy swimming and photography. I also occasionally share my thoughts on Zhihu.

📢 I am currently applying for recommended postgraduate programs. I am open to research opportunities and collaborations in related areas.

🔥 News

[06/2026] 🎉 One paper gets accepted by ECCV 2026.
[06/2026] I will serve as a reviewer for AAAI 2027.
[05/2026] 🎉 One paper gets accepted by ICML 2026.
[02/2026] 🎉 One paper gets accepted by CVPR 2026.
[01/2026] 🎉 One paper gets accepted by ICASSP 2026 (Oral).
[11/2025] 🏆 Awarded Fan Linhu Petroleum Scholarship.
[10/2025] 🏆 Awarded National Scholarship.
[10/2025] I will serve as a reviewer for CVPR 2026.
[09/2025] I will serve as a reviewer for ICASSP 2026.
[07/2025] I will serve as a reviewer for AAAI 2026.

📝 Publications

Mixture of Specialized Vision Experts framework

Mixture of Specialized Vision Experts: Unlocking Complementary Visual Insights for Faithful MLLM Reasoning

Yifei Gao, Liangliang You, Jiye Xie, Changwei Wang, Kexue Fu, Jingyi Liu, Rongtao Xu, Zhiqiang Kou, Haoran Xu, Longxiang Gao, Yu Zhang
European Conference on Computer Vision (ECCV), 2026. (CCF-B)

Adaptive Visual Autoregressive Acceleration via Dual-Linkage Entropy Analysis

Yu Zhang, Jingyi Liu†, Feng Liu, Duoqian Miao*, Qi Zhang, Kexue Fu, Changwei Wang, Longbing Cao
† Project Lead, * Corresponding Author
Forty-Third International Conference on Machine Learning (ICML), 2026. (CCF-A)

📄 Paper

Markovian Scale Prediction: A New Era of Visual Autoregressive Generation

Yu Zhang, Jingyi Liu†, Yiwei Shi, Qi Zhang, Duoqian Miao*, Changwei Wang, Longbing Cao
† Project Lead, * Corresponding Author
The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026(CVPR), 2026. (CCF-A)

📄 Paper 🍔 Project

Enhancing Quantization for Visual AutoRegressive Generation via Uncertainty Identification

Jingyi Liu, Guangyao Xiong, Shuxia Ren†, Ruoyang Gao, Linkun Yu, Kexue Fu
† Corresponding Author
2026 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2026 (Oral).

🎖 Honors and Awards

National Scholarship in 2025
Fan Linhu Petroleum Scholarship in 2025 (Top 2%)
Tongji University Geophysics Scholarship in 2024 (Top 5%)
First Prize, National Finals of Global Campus AI Algorithm Competition in 2024
Second Prize, National AI Application Innovation Challenge in 2024
Second Prize, 15th National College Mathematics Competition in 2023

📖 Educations

2023.09 - Now, Undergraduate, School of Ocean and Earth Science, Tongji Univeristy, Shanghai.

💻 Internships