Visual Tokens on Demand: Visual Budgeting for Scalable and Efficient Multi-Image Reasoning in Multimodal LLMs

Paper recorded by Signals 4 on 2026-10-13 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-13 on arXiv · recorded by Signals 4 on 2026-10-14

Category: cs.CV · 计算机视觉 · first seen 2026-10-14

Abstract

Multimodal large language models have advanced rapidly, but most remain optimized for single-image inputs. Multi-image reasoning is costly because each image adds many visual tokens, increasing encoding and attention demands. Existing techniques that address the above issue, including visual token pruning, token merging, visual token compression, learned resampling, hierarchical compression, retri

Read on arXiv →