edge-cloud inference 1multimodal large language models 1query-guided pruning 1training-free methods 1visual token pruning 1
From the 1 of 2 linked papers with an AI index.
2 papers
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…
cs.CV2026
Prior-Anchored Debiasing for Long-Tailed Multi-Organ Pathology Report Generation
Feng Yang, Jie Liu, Yubo Pang +5
Automated pathology report generation from Whole Slide Images (WSIs) has attracted increasing attention in digital pathology. However, existing methods are predominantly developed…