Skip to content
conftrace_
2025 ICML ICML 2025

Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

❓ The Questioner

Authors

shiqi chen, Tongyao Zhu, Ruochen Zhou, Jinghan Zhang, Siyang Gao, Juan Carlos Niebles, Mor Geva, Junxian He, Jiajun Wu, Manling Li

Topics

Artificial Intelligence > Core AI > Interpretability Deep Learning > Architectures > Transformers Artificial Intelligence > Core AI > Reasoning

Keywords

attention mechanism spatial reasoning image token focus area vlms text tokens
Download PDF