Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.20021 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913859630006272 |
|---|---|
| author | Chae, Hyunsik Yoon, Seungwoo Park, Jaden Chun, Chloe Yewon Cho, Yongin Cai, Mu Lee, Yong Jae Ryu, Ernest K. |
| author_facet | Chae, Hyunsik Yoon, Seungwoo Park, Jaden Chun, Chloe Yewon Cho, Yongin Cai, Mu Lee, Yong Jae Ryu, Ernest K. |
| contents | Recent Vision-Language Models (VLMs) have demonstrated impressive multimodal comprehension and reasoning capabilities, yet they often struggle with trivially simple visual tasks. In this work, we focus on the domain of basic 2D Euclidean geometry and systematically categorize the fundamental, indivisible visual perception skills, which we refer to as atomic visual skills. We then introduce the Atomic Visual Skills Dataset (AVSD) for evaluating VLMs on the atomic visual skills. Using AVSD, we benchmark state-of-the-art VLMs and find that they struggle with these tasks, despite being trivial for adult humans. Our findings highlight the need for purpose-built datasets to train and evaluate VLMs on atomic, rather than composite, visual perception tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_20021 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Decomposing Complex Visual Comprehension into Atomic Visual Skills for Vision Language Models Chae, Hyunsik Yoon, Seungwoo Park, Jaden Chun, Chloe Yewon Cho, Yongin Cai, Mu Lee, Yong Jae Ryu, Ernest K. Computer Vision and Pattern Recognition Artificial Intelligence Recent Vision-Language Models (VLMs) have demonstrated impressive multimodal comprehension and reasoning capabilities, yet they often struggle with trivially simple visual tasks. In this work, we focus on the domain of basic 2D Euclidean geometry and systematically categorize the fundamental, indivisible visual perception skills, which we refer to as atomic visual skills. We then introduce the Atomic Visual Skills Dataset (AVSD) for evaluating VLMs on the atomic visual skills. Using AVSD, we benchmark state-of-the-art VLMs and find that they struggle with these tasks, despite being trivial for adult humans. Our findings highlight the need for purpose-built datasets to train and evaluate VLMs on atomic, rather than composite, visual perception tasks. |
| title | Decomposing Complex Visual Comprehension into Atomic Visual Skills for Vision Language Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2505.20021 |