paper-with-me

Papers

GlyphPattern: An Abstract Pattern Recognition for Vision-Language Models

2024-08-12 · Zixuan Wu, Yoolim Kim, Carolyn Jane Anderson

Vision-Language Models (VLMs) building upon the foundation of powerful large language models have made rapid progress in reasoning across visual and textual data. While VLMs perform well on vision tasks that they are trained on, our results highlight key challenges in abstract pattern recognition. We present GlyphPattern, a 954 item dataset that pairs 318 human-written descriptions of visual patterns from 40 writing systems with three visual presentation styles. GlyphPattern evaluates abstract pattern recognition in VLMs, requiring models to understand and judge natural language descriptions of visual patterns. GlyphPattern patterns are drawn from a large-scale cognitive science investigation of human writing systems; as a result, they are rich in spatial reference and compositionality. Our experiments show that GlyphPattern is challenging for state-of-the-art VLMs (GPT-4o achieves only 55% accuracy), with marginal gains from few-shot prompting. Our detailed error analysis reveals challenges at multiple levels, including visual processing, natural language understanding, and pattern generalization.

📄 PDF Abstract BibTeX arXiv:2408.05894

Code (1)

Wellesley-EASEL-lab/GlyphPattern 공식 구현 pytorch

Tasks

Natural Language Understanding

Similar Papers 제목 키워드 기반

SEVA: Leveraging sketches to evaluate alignment between human and machine visual abstraction

2023-12-05 · NeurIPS 2023 11 · Kushin Mukherjee, Holly Huey, Xuanchen Lu, Yael Vinker 외

Sketching is a powerful tool for creating abstract images that are sparse but meaningful. Sketch understanding poses fundamental challenges for general-purpose vision algorithms because it requires robustness to the spar…

Sketch Recognition

Induction Heads as an Essential Mechanism for Pattern Matching in In-context Learning

2024-07-09 · Joy Crosbie, Ekaterina Shutova

Large language models (LLMs) have shown a remarkable ability to learn and perform complex tasks through in-context learning (ICL). However, a comprehensive understanding of its internal mechanisms is still lacking. This …

In-Context Learning

AR$^2$: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models

2025-08-27 · Cheng-Kai Yeh, Hsing-Wang Lee, Chung-Hung Kuo, Hen-Hsen Huang arxiv

Abstraction--the ability to recognize and distill essential computational patterns from complex problem statements--is a foundational skill in computer science, critical both for human problem-solvers and coding-oriented…

Reinforcement LearningCode Generation

Learning the Bitter Lesson: Empirical Evidence from 20 Years of CVPR Proceedings

2024-10-12 · Mojtaba Yousefi, Jack Collins

This study examines the alignment of \emph{Conference on Computer Vision and Pattern Recognition} (CVPR) research with the principles of the "bitter lesson" proposed by Rich Sutton. We analyze two decades of CVPR abstrac…

Bridging Vision, Language, and Mathematics: Pictographic Character Reconstruction with Bézier Curves

2025-10-29 · Zihao Wan, Pau Tong Lin Xu, Fuwen Luo, Ziyue Wang 외 arxiv

While Vision-language Models (VLMs) have demonstrated strong semantic capabilities, their ability to interpret the underlying geometric structure of visual information is less explored. Pictographic characters, which com…

Program Synthesis