Author

Yongkun Li

Observed name: Li, Yongkun

Institutions: University of Science and Technology of China, Chinese University of Hong Kong

Observed institutions: University of Science and Technology of China, Chinese University of Hong Kong

OpenAlex ID: A5159144961

Visual Cache Reuse for Efficient Multimodal Inference

2026 · Gao, Shuheng, Fan, Yuankai, et al. · arXiv (Cornell University)

gKSM: GPU Memory Deduplication at Driver Layer for Serverless LLM Inference

2026 · Gao, Shuheng, Guo, Fan, et al. · arXiv (Cornell University)

Works count: 2

Citation count:

H-index:

I10-index: