1 code implementation • 23 Mar 2024 • HAZ Sameen Shahgir, Khondker Salman Sayeed, Abhik Bhattacharjee, Wasi Uddin Ahmad, Yue Dong, Rifat Shahriyar
GPT4V, the best-performing VLM, achieves 62. 99% accuracy (4-shot) on the comprehension task and 49. 7% on the localization task (4-shot and Chain-of-Thought).
Ranked #1 on Object Localization on IllusionVQA
no code implementations • 22 Jan 2024 • HAZ Sameen Shahgir, Khondker Salman Sayeed, Md Toki Tahmid, Tanjeem Azwad Zaman, Md. Zarif Ul Alam
Recent advances in Deep Learning and Computer Vision have been successfully leveraged to serve marginalized communities in various contexts.
1 code implementation • 22 Dec 2023 • HAZ Sameen Shahgir, Xianghao Kong, Greg Ver Steeg, Yue Dong
The widespread use of Text-to-Image (T2I) models in content generation requires careful examination of their safety, including their robustness to adversarial attacks.
1 code implementation • 16 Mar 2023 • HAZ Sameen Shahgir, Ramisa Alam, Md. Zarif Ul Alam
Named Entity Recognition (NER) is a fundamental task in natural language processing that involves identifying and classifying named entities in text.