Poster · Paris

CECAR: Cache & Expert Co-Aware Routing Accelerates On-Device Inference of MoE LLMs

Name: CECAR: Cache & Expert Co-Aware Routing Accelerates On-Device Inference of MoE LLMs
Start: 2026-12-10T17:30:00+01:00
End: 2026-12-10T19:30:00+01:00
Location: Paris Poster Hall, Paris

When: Thu 10 Dec 2026, 17:30–19:30 CET
Where: Paris Poster Hall
Session: Paris Poster Session 4
Authors: Byeongju Kim, Hoonki Lee, Byungjun Kim, Inyul Ra, Yongjin Kim, Yongseong Lee, Sangyeob Kim
Organisations: KAIST, Agency for Defense Development, Yonsei University
QRS classification: Language models

Open in schedule Official page