activity
20242026
most citedEMS: Adaptive Evict-then-Merge Strategy for Head-wise KV Cache Compression Based on Global-Local Importance

1 citations · 1 across the 15 of their papers we have counts for

collaborators
Showing 2024 · cs.CVShow all

1 paper · 2 filters

cs.CV2024

PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference

Ye Li, Chen Tang, Yuan Meng +5

We introduce PRANCE, a Vision Transformer compression framework that jointly optimizes the activated channels and reduces tokens, based on the characteristics of inputs. Specifical…