Xubing Ye (叶栩冰)

Now, I am a 2nd year master at Shenzhen International Graduate School, Tsinghua University (M.Eng.@THU’2026), supervised by Prof. Yansong Tang. I obtained my bachelor's degree from the School of Software Engineering at Tongji University in 2023. I was a research intern at Tencent ARC Lab where I worked with Dr. Yukang Gan, Dr. Yixiao Ge, and Dr. Ying Shan. I also collaborated with Dr. Zhao Yang at Shanghai AI Lab.

My current research interest lies at Multi-Modal Large Language Models (MLLMs), efficient MLLMs, and video understanding.

Email: yxb_tongji@163.com  /  Github  /  Scholar  /  X

* Indicates Equal Contribution

We propose VoCo-LLaMA, the first approach to compress vision information utilizing the LLMs' understanding paradigm, which can compress hundreds of vision tokens into a single VoCo token with minimal visual information loss.

We propose ATP-LLaVA, a framework that adaptively determines pruning ratios instance-wise and LLM layer-wise for effective vision token pruning on large vision language models.

We propose LAVT, a Transformer-based universal referring image and video segmentation (RIS and RVOS) framework that performs language-aware visual encoding in place of cross-modal fusion post feature extraction.

Industrial Experience