Published in Heliyon, 2024
A research article proposing a context-aware attention mechanism that improves image caption generation by better modeling the interaction between visual features and the linguistic context generated so far.
Recommended citation: Bhuiyan, A. (2024). "Enhancing Image Caption Generation Through Context-Aware Attention Mechanism." Heliyon, 10(17). Research Article.
Published in 2024 27th International Conference on Computer and Information Technology (ICCIT), 2024
A conference paper proposing an attentive fusion framework for detecting misinformation from multi-modal (text and image) content.
Recommended citation: Mehreen, S., Bhuiyan, A., & Hossain, E. (2024). "An Attentive Fusion Framework for Multi-Modal Misinformation Detection." 2024 27th International Conference on Computer and Information Technology (ICCIT).
Published in arXiv preprint arXiv:2601.03435, 2026
A preprint examining how aspect-level information affects the measurement of document similarity.
Recommended citation: Hossain, E., Hazra, T., Bhuiyan, A., & Karmaker, S. (2026). "The Critical Role of Aspects in Measuring Document Similarity." arXiv preprint arXiv:2601.03435.
Download Paper
Published in arXiv preprint arXiv:2607.18126, 2026
A preprint introducing CutBackdoor, a backdoor attack on variational quantum algorithms triggered via circuit cutting.
Recommended citation: Bhuiyan, A., Ngo, H., Chu, C., Lou, Q., Jiang, L., Thai, M. T., & Zheng, M. (2026). "CutBackdoor: A Circuit Cut Triggered Backdoor Attack on Variational Quantum Algorithms." arXiv preprint arXiv:2607.18126.
Download Paper
Published in QCE26 2nd Workshop on Quantum Computing Security, Privacy & Resilience (Q-Sec), 2026
Accepted paper studying the robustness of sample-based quantum diagonalization methods under real hardware noise.
Recommended citation: Bhuiyan, A., Chu, C., Lou, Q., & Zheng, M. (2026). "Hardware Robustness of Sample-Based Quantum Diagonalization." QCE26 2nd Workshop on Quantum Computing Security, Privacy & Resilience (Q-Sec).
Download Paper