大模型
arxiv.org ·
BrainFocus：面向高效视觉-语言模型的脑电图引导 ROI 选择
该论文提出 BrainFocus，一种 EEG 引导的高效 VLM 框架：EEG 分类器预测目标类别，YOLO 检测器定位对应 ROI，仅当两者均通过置信度阈值时 VLM 才处理裁剪后的 ROI，否则处理整图。作者基于 EEG-ImageNet 构建 40 类基准（含生成式杂乱图像与真实物体中心图像、目标 ROI 标注及 600 条英文 VQA 对）。在 Qwen3.5-VL 2B、4B、9B 上，杂乱场景 VQA 准确率提升 4.14–9.87 个百分点，输入 token 与总 token 减少 23.2%–39.4%，端到端 FLOPs 减少 23.2%–39.5%。
AI推荐理由 arXiv 新论文，摘要给出明确方法（EEG 分类器预测类别 + YOLO 定位 ROI，双阈值置信度决定是否裁剪）与可量化结果：在 Qwen3.5-VL 2B/4B/9B 上，杂乱场景 VQA 准确率提升 4.14–9.87 个百分点，输入 token 与总 token 减少 23.2%–39.4%，端到端 FLOPs 减少 23.2%–39.5%。新信息在于用 EEG 作为人类语义线索引导 VLM 高效推理，并自建 40 类基准（含 600 条英文 VQA 对）。局限：结果均为作者自报，基准为自建，EEG 引导依赖额外硬件，实际部署价值待验证。
72
正文
Computer Science > Computer Vision and Pattern Recognition
arXiv:2609.17443 (cs)
[Submitted on 15 Sep 2026]
Title:BrainFocus: EEG-Guided ROI Selection for Efficient Vision-Language Models
Authors:Yihui Peng, Guorui Lu, Qinyu Chen
View a PDF of the paper titled BrainFocus: EEG-Guided ROI Selection for Efficient Vision-Language Models, by Yihui Peng and 2 other authors
View PDF
HTML (experimental)
Abstract:Vision-language models (VLMs) achieve strong visual question answering (VQA) performance, but processing large cluttered images is computationally expensive when only a small region is relevant. Electroencephalography (EEG) signals, which capture human neural responses to visual stimuli, can provide a human-derived semantic cue about the region of interest (ROI). However, EEG-guided visual category decoding remains imperfect, making direct ROI routing unreliable. In this work, we propose BrainFocus, a reliable EEG-guided efficient VLM framework for VQA. An EEG classifier predicts a target category, and a YOLO detector localizes the matching ROI. The VLM receives the cropped ROI only when both predictions pass confidence thresholds; otherwise, it processes the full image. For evaluation, we build on EEG-ImageNet to construct a 40-class benchmark comprising generated cluttered images and real object-centric images, with target-ROI annotations and 600 English visual question-answer pairs. Across Qwen3.5-VL 2B, 4B, and 9B models, BrainFocus improves VQA accuracy by 4.14-9.87 percentage points (pp) on cluttered scenes while reducing input tokens and total tokens by 23.2%-39.4% and 23.2%-39.3%, and end-to-end floating-point operations (FLOPs) by 23.2%-39.5%. These results demonstrate that EEG can guide efficient VLM inference even when its semantic decoding is imperfect.
Subjects:
Computer Vision and Pattern Recognition (cs.CV)
Cite as:
arXiv:2609.17443 [cs.CV]
(or
arXiv:2609.17443v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2609.17443
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Yihui Peng [view email]
[v1]
Tue, 15 Sep 2026 16:51:13 UTC (3,297 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled BrainFocus: EEG-Guided ROI Selection for Efficient Vision-Language Models, by Yihui Peng and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)