5 papers
On Threshold Pairwise Compatibility Graphs
Sheikh Azizul Hakim, Md. Shamsuzzoha Bayzid
Pairwise Compatibility Graphs (PCGs) form a tree-metric graph class that originated in phylogeny and has since attracted sustained interest in graph theory. Several natural general…
Pairwise Compatibility Representations of Multidimensional Grid Graphs
Sheikh Azizul Hakim, Md. Shamsuzzoha Bayzid
Pairwise compatibility graphs (PCGs) represent graph adjacency by an interval of leaf-to-leaf distances in a weighted tree. We study grid graphs under the PCG model and two natural…
An Explorative Study on Distributed Computing Techniques in Training and Inference of Large Language Models
Sheikh Azizul Hakim, Saem Hasan
Large language models (LLM) are advanced AI systems trained on extensive textual data, leveraging deep learning techniques to understand and generate human-like language. Today's L…
Isotropy and Geometry of Pretrained Protein LMs
Sheikh Azizul Hakim, Kowshic Roy, M Saifur Rahman
Large pretrained language models have transformed natural language processing, and their adaptation to protein sequences -- viewed as strings of amino acid characters -- has advanc…
DFCon: Attention-Driven Supervised Contrastive Learning for Robust Deepfake Detection
MD Sadik Hossain Shanto, Mahir Labib Dihan, Souvik Ghosh +8
This report presents our approach for the IEEE SP Cup 2025: Deepfake Face Detection in the Wild (DFWild-Cup), focusing on detecting deepfakes across diverse datasets. Our methodolo…