Pooyan Rahmanzadehgervi

According to our database, Pooyan Rahmanzadehgervi authored at least 5 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Vision Language Models Cannot Reason About Physical Transformation.

Dezhi Luo, Yijiang Li, Maijunxian Wang, Tianwei Zhao, Bingyang Wang, Siheng Wang, Pinyuan Feng, Pooyan Rahmanzadehgervi, Ziqiao Ma, Hokin Deng

CoRR, March, 2026

2025

Improving Zero-Shot Object-Level Change Detection by Incorporating Visual Correspondence.

Hung Huy Nguyen, Pooyan Rahmanzadehgervi, Long Mai, Anh Totti Nguyen

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2025

TAB: Transformer Attention Bottlenecks Enable User Intervention and Debugging in Vision-Language Models.

Pooyan Rahmanzadehgervi, Hung Huy Nguyen, Rosanne Liu, Long Mai, Anh Totti Nguyen

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

2024

Vision language models are blind.

Pooyan Rahmanzadehgervi, Logan Bolton, Mohammad Reza Taesiri, Anh Totti Nguyen

CoRR, 2024

Vision Language Models are blind 🕶.

Pooyan Rahmanzadehgervi, Logan Bolton, Mohammad Reza Taesiri, Anh Totti Nguyen

Proceedings of the Computer Vision - ACCV 2024, 2024