๐ I am Xuyang Liu (ๅๆญๆด), an incoming PhD student at PolyU, where I will join the VC Lab under the supervision of Chair Prof. Lei Zhang (IEEE Fellow). I am also currently working as a research intern at OPPO Research Institute. Previously, I earned my M.S. from Sichuan University and spent a wonderful year interning at Alibaba Group and Ant Group. I am fortunate to work closely with Dr. Siteng Huang and Prof. Linfeng Zhang.
๐ My research centers on Efficient Multimodal Large Language Models (MLLMs), including:
- ๐ผ๏ธ Image Understanding: high-resolution understanding via context compression and fast decoding, including GlobalCom2[AAAI'26], V2Drop[CVPR'26], FiCoCo[AAAI'26], and MixKV[ICLR'26].
- ๐ฌ Video Understanding: long/audio-video, and streaming reasoning via efficient encoding and compression, including VidCom2[EMNLP'25], STC[CVPR'26], V-CAST, and OmniSIFT[ICML'26].
- ๐จ Content Generation: lightweight and efficient AIGC via feature caching, pruning, and fast decoding, including ToCa[ICLR'25], Flash-Unified[CVPR'26 Findings], and STDec.
- โ๏ธ Efficiency Toolbox: efficient transfer/fine-tuning and benchmarking for downstream task adaptation, including M2IST[TCSVT'25], V-PETL[NeurIPS'24], and AutoGnothi[ICLR'25].
๐ข If you find these directions interesting, feel free to reach out via email: liuxuyang@stu.scu.edu.cn. I am actively seeking internship opportunities!