Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
Reasoning under Vision: Understanding Visual-Spatial Cognition in Vision-Language Models for CAPTCHA
Python Song, Luke Tenyi Chang, Yun-Yun Tsai +2
CAPTCHA, originally designed to distinguish humans from robots, has evolved into a real-world benchmark for assessing the spatial reasoning capabilities of vision-language models.…
cs.CV2024
GDA: Generalized Diffusion for Robust Test-time Adaptation
Yun-Yun Tsai, Fu-Chen Chen, Albert Y. C. Chen +4
Machine learning models struggle with generalization when encountering out-of-distribution (OOD) samples with unexpected distribution shifts. For vision tasks, recent studies have…