paper-with-me

홈 › Papers

Multimodal LLMs Struggle with Basic Visual Network Analysis: a VNA Benchmark

2024-05-10 · Evan M. Williams, Kathleen M. Carley

We evaluate the zero-shot ability of GPT-4 and LLaVa to perform simple Visual Network Analysis (VNA) tasks on small-scale graphs. We evaluate the Vision Language Models (VLMs) on 5 tasks related to three foundational network science concepts: identifying nodes of maximal degree on a rendered graph, identifying whether signed triads are balanced or unbalanced, and counting components. The tasks are structured to be easy for a human who understands the underlying graph theoretic concepts, and can all be solved by counting the appropriate elements in graphs. We find that while GPT-4 consistently outperforms LLaVa, both models struggle with every visual network analysis task we propose. We publicly release the first benchmark for the evaluation of VLMs on foundational VNA tasks.

📄 PDF Abstract BibTeX arXiv:2405.06634

Code (1)

evanup/vna_benchmark 공식 구현

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Position-Wise Feed-Forward Layer 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

2024-01-11 · CVPR 2024 1 · Shengbang Tong, Zhuang Liu, Yuexiang Zhai, Yi Ma 외

Is vision good enough for language? Recent advancements in multimodal models primarily stem from the powerful reasoning abilities of large language models (LLMs). However, the visual component typically depends only on t…

Representation LearningSelf-Supervised LearningVisual Grounding

Why Text Prevails: Vision May Undermine Multimodal Medical Decision Making

2025-12-15 · Siyuan Dai, Lunxiao Li, Kun Zhao, Eardi Lila 외 arxiv

With the rapid progress of large language models (LLMs), advanced multimodal large language models (MLLMs) have demonstrated impressive zero-shot capabilities on vision-language tasks. In the biomedical domain, however, …

Decision Making

Burn After Reading: Do Multimodal Large Language Models Truly Capture Order of Events in Image Sequences?

2025-06-12 · Yingjin Song, Yupei Du, Denis Paperno, Albert Gatt

This paper introduces the TempVS benchmark, which focuses on temporal grounding and reasoning capabilities of Multimodal Large Language Models (MLLMs) in image sequences. TempVS consists of three main tests (i.e., event …

SentenceSentence Ordering

Face-MLLM: A Large Face Perception Model

2024-10-28 · Haomiao Sun, Mingjie He, Tianheng Lian, Hu Han 외

Although multimodal large language models (MLLMs) have achieved promising results on a wide range of vision-language tasks, their ability to perceive and understand human faces is rarely explored. In this work, we compre…

AttributemodelQuestion AnsweringVisual Question Answering

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models

2025-08-09 · Jianting Tang, Yubo Wang, Haoyu Cao, Linli Xu arxiv

Mainstream Multimodal Large Language Models (MLLMs) achieve visual understanding by using a vision projector to bridge well-pretrained vision encoders and large language models (LLMs). The inherent gap between visual and…