Pooyan Rahmanzadehgervi — accepted AI-conference papers

2026

Vision Language Models Cannot Reason About Physical Transformation

Dezhi Luo, Yijiang Li, Maijunxian Wang, Tianwei Zhao, Bingyang Wang, siheng wang +4

ICML 2026poster

Understanding physical transformations is fundamental for reasoning in dynamic environments. While Vision Language Models (VLMs) show promise in embodied applications, whether they genuinely understand physical transformations remains unclear. We introduce ***ConservationBench*** evaluating ***conse…

Cited by 0 Source ↗Scholar ↗

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

ICCV 2025poster

Multi-head self-attention (MHSA) is a key component of Transformers, a widely popular architecture in both language and vision. Multiple heads intuitively enable different parallel processes over the same input. Yet, they also obscure the attribution of each input patch to the output of a model. We…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗