Yuankai Fan
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper introduces Arachne, a framework for efficient Text-to-Video model training at scale, reducing iteration time by up to 65% over leading frameworks.
VisMemo is a serving system that enables approximate KV cache reuse for modern vision-language models to reduce prefill latency and memory overhead.
Papers
Visual Cache Reuse for Efficient Multimodal Inference
Shuheng Gao, Yuankai Fan, Jiaqiang Ma, Jiawei Shao +2 more
VisMemo is a serving system that enables approximate KV cache reuse for modern vision-language models to reduce prefill latency and memory overhead.