Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Pooyan Rahmanzadehgervi
Observed names:
Pooyan R,
Rahmanzadehgervi, Pooyan
Institution:
Auburn University
Observed institution:
Auburn University
OpenAlex ID:
A5103305861
Vision Language Models are blind
2024
·
Pooyan Rahmanzadehgervi
, Logan Bolton
, et al.
·
Lecture notes in computer science
·
39
Improving Zero-Shot Object-Level Change Detection by Incorporating Visual Correspondence
2025
·
Hung H. Nguyen
, Pooyan Rahmanzadehgervi
, et al.
·
IEEE Winter Conference on Applications of Computer Vision
·
6
PDF
TAB: Transformer Attention Bottlenecks Enable User Intervention and Debugging in Vision-Language Models
2025
·
Pooyan Rahmanzadehgervi
, Hung Huy Nguyen
, et al.
·
IEEE/CVF International Conference on Computer Vision (ICCV)
·
1
PDF
anguyen8/vision-llms-are-blind: official
2026
·
Pooyan R
, Mohammad Reza Taesiri
, et al.
·
Zenodo (CERN European Organization for Nuclear Research)
Vision Language Models Cannot Reason About Physical Transformation
2026
·
Luo, Dezhi
, Li, Yijiang
, et al.
·
arXiv (Cornell University)
PDF
Vision language models are blind: Failing to translate detailed visual features into words
2024
·
Rahmanzadehgervi, Pooyan
, Bolton, Logan
, et al.
·
arXiv (Cornell University)
PDF
Show more works
View as search
Works count:
7
Citation count:
46
H-index:
2
I10-index:
1
Year
Topic
Type
