8 papers
Revisiting Ground-Truth Synthesis from High-Speed Video: Exact Validity Conditions and an Audited Consumer Capture Corpus
Abdullah Al Shafi, Sumaiya Rahim Suma
Motion-deblurring datasets are commonly synthesised by averaging consecutive high-frame-rate frames and labelling the result with the central frame. We show that this label is…
Bangla Sentence Function Classification: Corpus Development, Model Benchmarking, and Interpretability
Swapnil Kundu Argha, Abdullah Al Shafi, Rowzatul Zannat +4
Automatic sentence function identification is important for many downstream natural language processing (NLP) applications such as dialogue systems, text-to-speech synthesis, and m…
Evolution of Multimodal Question Answering: From Modality-Adaptive Extraction to Unified Language Representation
Abdullah Al Shafi
The rapid growth of multimodal data has intensified the need for question answering (QA) systems capable of reasoning across heterogeneous sources such as text, tables, and images.…
Attention-Enhanced Deep Features with Heterogeneous Ensemble Learning for Glaucoma Detection
Abdullah Al Shafi, Nishat Sadaf Lira, Abrar Hasan +2
Glaucoma is a progressive optic neuropathy characterized by irreversible damage to the optic nerve, making timely diagnosis critical to prevent permanent vision loss. Although deep…
BanglaMed-QA: A Question Answering System for Healthcare Support in Bangla
Rowzatul Zannat, Abdullah Al Shafi, K. M. Azharul Hasan +1
Medical question answering (QA) systems have become crucial tools for providing reliable health information. But they remain very unexplored for low-resource languages like Bangla…
Closing the Null Space: Guidance-Aware Quantization for Classifier-Free Diffusion
Abdullah Al Shafi, Sumaiya Rahim Suma
Deploying classifier-free guidance (CFG) diffusion models under real-world compute budgets requires quantization, yet existing post-training quantization (PTQ) methods treat CFG mo…
Towards Developing a Multimodal Chat Assistant for University Stakeholders: RAG-based Approach
Md Abu Hanif Shaikh, Abdullah Al Shafi
University stakeholders often face difficulties in accessing timely and reliable information, especially in developing countries, where there are very few intelligent support syste…
StanceMoE: Mixture-of-Experts Architecture for Stance Detection
Abdullah Al Shafi, Md. Milon Islam, Sk. Imran Hossain +1
Actor-level stance detection aims to determine an author expressed position toward specific geopolitical actors mentioned or implicated in a text. Although transformer-based models…