- I'm currently in the field of Efficient Vision Large Language Modeling (vLLM) Research
- My primary research direction is AIGC including diffusion synthesis and large language models.
- Check out my recent research at MiniCache | Motion Mamba | BPKD | SegViTv2
- Check out my recent CV/NLP/AML coursework at CV′3315 Is All You Need | External Reasoning | Personalised Video Generation
- Preferable Programming Language (Research) --
- Interested in machine learning, artificial intelligence, and Computer Vision.
- Experienced in cloud computing and virtualization, including vSphere cluster, Kubernetes cluster, and rancher.
- Research Contact: akide (dot) liu (at) monash (dot) edu
- Other Enquiries: mail+research (at) llycloud (dot) com