2 papers
cs.LG2026
RelayCaching: Accelerating LLM Collaboration via Decoding KV Cache Reuse
Yingsheng Geng, Yuchong Gao, Weihong Wu +2
The increasing complexity of AI tasks has shifted the paradigm from monolithic models toward multi-agent large language model (LLM) systems. However, these collaborative architectu…
cond-mat.soft2025
Geometrically Templated Dynamic Wrinkling from Suspended Poly(vinyl alcohol) Soap Films
Yuchong Gao, Yinding Chi, Mohit Patel +4
Wrinkling is commonly observed as mechanical instability when a stiff thin film bound on a compliant thick substrate undergoes in-plane compression exceeding a threshold. Despite s…