2026
SPLIT-VLM: Salience-Guided Partitioning towards Local Coverage for Importance-Aware Token Dropping in Vision-Language Models
ICML 2026poster
Large-scale vision–language models (VLMs) excel at multimodal reasoning, yet efficiency collapses when vision tokens—often orders of magnitude more than text—dominate compute and memory. Prior token-reduction strategies typically trade off salience (which is prone to position bias and incurs extra c…