π I am Xuyang Liu (εζζ΄), a third-year Master's student at Sichuan University. I am also working as a research intern at OPPO Research Institute, supervised by Prof. Lei Zhang (PolyU, IEEE Fellow). Previously, I have interned at Ant Group focusing on GUI Agent, and Taobao & Tmall Group working on Efficient VLMs. I've also spent half a year visiting MiLAB at Westlake University, supervised by Prof. Donglin Wang. I am fortunate to work closely with Dr. Siteng Huang from DAMO Academy and Prof. Linfeng Zhang from SJTU.
π My research centers on efficient Large Vision-Language Models (LVLMs), including:
- πΌοΈ Image-Text LVLMs: high-resolution understanding via context compression and fast decoding.
- π¬ Video Understanding: long/audio-video, and streaming reasoning via efficient encoding and compression.
- βοΈ Efficiency Toolbox: efficient transfer/fine-tuning and benchmarking for downstream task adaptation.
π’ If you find these directions interesting, feel free to reach out via email: [email protected].