English

Decoding the Pulse of Reasoning VLMs in Multi-Image Understanding Tasks

Computer Vision and Pattern Recognition 2026-05-11 v2 Artificial Intelligence

Abstract

Multi-image reasoning remains a significant challenge for vision-language models (VLMs). We investigate a previously overlooked phenomenon: during chain-of-thought (CoT) generation, the text-to-image (T2I) attention of reasoning VLMs exhibits diffuse "pulses": sporadic and unfocused attention patterns that fail to concentrate on task-relevant images. We further reveal a systematic positional bias in attention allocation across images. Motivated by these observations, we propose PulseFocus, a training-free, inference-time method that structures CoT reasoning into interleaved plan/focus blocks with soft attention gating. By forcing the model to explicitly plan which image to examine and then gating decode-time attention to the referenced image, PulseFocus sharpens attention focus and yields consistent improvements on multi-image benchmarks like BLINK benchmark (+3.7%) and MuirBench (+1.07%).

Keywords

Cite

@article{arxiv.2603.04676,
  title  = {Decoding the Pulse of Reasoning VLMs in Multi-Image Understanding Tasks},
  author = {Chenjun Li},
  journal= {arXiv preprint arXiv:2603.04676},
  year   = {2026}
}

Comments

This article is withdrawn because the experimental results and analysis require substantial revision. The current version should not be cited as a reliable representation of the work

R2 v1 2026-07-01T11:04:05.315Z