most citedScissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time

11 citations · 11 across the 1 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

Just Respect the Semantics: Image-Token Compression via Pre-LLM Semantic Variable-Resolution Tokenization and In-LLM Relevance Pruning

Tianhao Fu, Austin Wang, Charles Chen +5

Image-token compression must reduce computation without hurting the semantics. We introduce Varest, guided by semantic fungibility: tokens within a coherent semantic region can be…