works on
edge-cloud inference 1multimodal large language models 1query-guided pruning 1training-free methods 1visual token pruning 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.CV2026

LAST: The Last Query Token Guides Visual Token Pruning for Edge-Cloud Collaborative MLLM Inference

Feng Yang, Xinrui Ju, Keyang Zhang +6

The paper introduces LAST, a training‑free method that uses the attention of the last query token to prune visual tokens on edge devices before sending them to a cloud multimodal L…