Development of machine learning and deep learning models for problems in various fields of sciences (particle physics, astronomy, biology etc) and application development based on Artificial Intelligence.
The Artificial Intelligence and Cybernetics (AGenCy) lab at the Independent University Bangladesh (IUB) was established in 2010, previously known as the Computer Vision and Cybernetics Research Lab. The lab is dedicated to education and research in the theory and application of Artificial Intelligence and Cybernetics. It focuses on developing computational models for data representation, visualization, and analysis in various fields of study, including but not limited to Computer Vision, Natural Language Processing, Environmental and Geospatial data analysis, Bioinformatics, Particle physics and Astrophysics, Rehabilitation and Sports technology, and IoT and Robotics.
The lab’s main focus is on developing and utilizing models and tools from probabilistic machine learning, deep learning, signal processing, and statistical inference. Given the multidisciplinary nature of the problems they address, the lab consists of faculty, graduate and undergraduate students, as well as collaborators from multiple disciplines, including computer science and engineering, electrical engineering, physics, mathematics, economics, and environmental science departments from IUB and other renowned universities both domestically and internationally.
Link to the previous website.
Professor
Department of Computer Science and Engineering
Independent University, Bangladesh (IUB)
Published at
ACL, CHI, UbiComp, ECCV, IJCAI, ECAI, WACV, IPSN, PAKDD, LREC, IJCNN, ICPR, ICIP, BEA, BLP, ICMLA, Scientific Reports, Scientific Data, Pattern Recognition, Information Sciences, Ad Hoc Networks, Drug and Alcohol Dependence, PLOS ONE
Professor
Department of Information Sciences and Technology
George Mason University, USA
Honorary Professor
Department of Computer Science and Engineering
Independent University, Bangladesh (IUB)Published at
ACL, CHI, UbiComp, ECAI, WACV, PAKDD, IJCNN, ICPR, ICIP, HCII, CLEF, BLP, Scientific Reports, Pattern Recognition, JMIR, IEEE Access, Smart Agricultural Technology, Frontiers in Computational Neuroscience, Diabetes Research and Clinical Practice, PLOS ONE
Assistant Professor
Imam Muhammad ibn Saud Islamic University
Generative AI Leadership
Amazon Web Services
Published at
ECCV
Ph.D Candidate
University of Massachusetts Amherst, USA
Published at
CHI
Assistant Professor
University of Wisconsin–Green Bay, USA
Assistant Professor
Department of Computer Science
Penn State Abington, USA
Professor
Institute of Information Technology
University of Dhaka, Bangladesh
Published at
Pattern Recognition
Applied Scientist II
GenAI Innovation Center
Amazon Web Services
Published at
ECCV
Ph.D Candidate
University of Illinois Urbana-Champaign, USA
Senior Research Scientist
Microsoft Research
PhD
McGill University, Canada
Assistant Professor
Department of Computer and Information Science
Fordham University
Senior Lecturer
School of Information and Physical Sciences
University of Newcastle, Australia
Ph.D Candidate
Curtin University, Australia
Published at
IJCNN
Postdoctoral Researcher
Department of Electrical Engineering and Automation
Aalto University
Trajectory-user linking identifies the likely user behind an anonymous mobility trace, but existing methods often lose fine-grained spatial, temporal, and semantic information or scale poorly.…
View project
This project studies how to make the reasoning produced by medical LLMs more factually reliable, not just their final answers. We construct controlled incorrect rationales with known clinically…
View project
This project studies when error detection and intervention can reliably improve multi-agent LLM systems, where mistakes from one agent may propagate through later interactions and affect the team’s…
View project
Personalized Federated Test-Time Adaptation studies how decentralized models can adapt to changing domains while also remaining robust to severe class imbalance across clients. Existing federated…
View project
Federated Test-Time Adaptation (FTTA) studies how decentralized models can adapt to client-specific distribution shifts at test time using unlabeled local data, without sharing raw data. This project…
View project
Source-Free Federated Test-Time Prompt Tuning (SF-FTTPT) studies how vision-language models can collaboratively adapt prompts at test time when clients have private, heterogeneous data with no access…
View project
Large language models serve speakers of hundreds of languages, yet most of what is known about their inner workings comes from English. Recent interpretability research shows that abstract concepts,…
View project
Modern spoken language systems convert raw audio into compact discrete representations that downstream models generate from and reason over. The central constraint is compression: as few tokens per…
View projectHasan, Syed Md. Ahnaf, Iftee, Md Akil Raihan, Mistry, Sajib, Ali, Amin Ahsan, Rahman, AKM Mahbubur
arXiv (Cornell University), 2026
Abu Tyeb Azad, Fahim Ahmed, Ishita Sur Apan, Ezharuddin Jubaer, Sumaiya Karim Katha, Armun Alam, Amin Ahsan Ali, Aman Chadha, Md Mofijul Islam, AKM Mahbubur Rahman
arXiv (Cornell University), 2026
Abu Tyeb Azad, Ishita Sur Apan, Fahim Ahmed, Sumaiya Karim Katha, Ezharuddin Jubaer, Armun Alam, Pranjal Kumar Nandi, Amin Ahsan Ali, Aman Chadha, Md Mofijul Islam, AKM Mahbubur Rahman
Computer Vision – ECCV 2026, pp. 402-420, 2026
Md Akil Raihan Iftee, Syed Md Ahnaf Hasan, Amin Ahsan Ali, AKM Mahbubur Rahman, Sajib Mistry, Aneesh Krishna
arXiv (Cornell University), pp. 3330-3339, 2025
Md Akil Raihan Iftee, Syed Md Ahnaf Hasan, Mir Sazzat Hossain, Rakibul Hasan Rajib, Amin Ahsan Ali, AKM Mahbubur Rahman, Sajib Mistry, Monowar Bhuyan
arXiv (Cornell University), 2025
