works on
evidence routing 1high-resolution visual question answering 1memory efficiency 1multimodal large language models 1single-pass inference 1

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

collaborators

1 paper

cs.CV2026

Thinking Once Is Enough: Intermediate-Layer Evidence Routing for High-Resolution VQA

Zhongkuan Mao, Xianjie Liu, Tianyu Meng +9

The paper proposes a training‑free, single‑pass method that routes intermediate‑layer visual evidence to improve high‑resolution visual question answering without extra image proce…