Too Late to Train, Too Early To Use? A Study on Necessity and Viability of Low-Resource Bengali LLMs
Published in arXiv, 2024
Tamzeed Mahfuz, Satak Kumar Dey, Ruwad Naswan, Hasnaen Adil, Khondker Salman Sayeed, Haz Sameen Shahgir.
Paper Link here
Posts by Collection
publications
Asymmetric Bias in Text-to-Image Generation with Adversarial Attacks
Published in Findings of ACL 2024, 2024
Haz Shahgir, Xianghao Kong, Greg Ver Steeg, Yue Dong
Paper Link here
IllusionVQA: A Challenging Optical Illusion Dataset for Vision-Language Models
Published in COLM 2024, 2024
Haz Shahgir*, Khondker Sayeed*, Abhik Bhattacharjee, Wasi Ahmad, Yue Dong, Rifat Shahriyar
Paper Link here
Leveraging Complementary Attention Maps in Vision Transformers for OCT Image Analysis
Published in ICIP 2025, 2025
Haz Shahgir*, Tanjeem Azwad Zaman*, Khondker Sayeed, Asif Haider, Sheikh Rahman, Sohel Rahman
Paper Link here
ExpertGenQA: Open-ended QA Generation in Specialized Domains
Published in Findings of EMNLP 2025, 2025
Haz Shahgir, Chansong Lim, Jia Chen, Evangelos E. Papalexakis, Yue Dong
Paper Link here
BiRNA-BERT Allows Efficient RNA Language Modeling with Adaptive Tokenization
Published in Nature Communications Biology, 2025
Md. Toki Tahmid*, Haz Shahgir*, Sazan Mahbub, Yue Dong, Shamsuzzoha Bayzid
Paper Link here
Harnessing the Unseen: The Hidden Influence of Intrinsic Knowledge in Long-Context Language Models
Published in AAAI 2026, 2026
Yu Fu, Haz Shahgir, Hui Liu, Xianfeng Tang, Qi He, Yue Dong
Paper Link here
D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output Rewriting
Published in ICML 2026, 2026
Huanli Gong*, Zhipeng Wei*, Yu Fu, Haz Shahgir, Ananya Gupta, Yue Dong, N. Benjamin Erichson
Paper Link here
VLMs Need Words: Vision-Language Models Ignore Visual Detail in Favor of Semantic Anchors
Published in COLM 2026, 2026
Haz Shahgir, Xiaofu Chen, Yu Fu, Erfan Shayegani, Nael Abu-Ghazaleh, Yova Kementchedjhieva, Yue Dong
Paper Link here
AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusion
Published in NeurIPS 2026, 2026
Abrar Rahman Abir*, Haz Shahgir*, Rownok Zahan Ratul, Toki Tahmid, Greg Ver Steeg, Yue Dong
Paper Link here
Do Reasoning LLMs Refuse What They Infer in Long Contexts?
Published in NeurIPS 2026, 2026
Yu Fu, Haz Shahgir, Zhipeng Wei, Huanli Gong, N. Benjamin Erichson, Yue Dong
Paper Link here
talks
ACL 2024 tutorial: Vulnerabilities of large language models to adversarial attacks
Published:
A tutorial on how safety-aligned language and multimodal models still fail under adversarial pressure, organized around text-only attacks, multimodal attacks, causes, and defenses.
BiRNA-BERT: Efficient RNA language modeling with adaptive tokenization
Published:
A walkthrough of dual NUC/BPE tokenization for RNA, why truncation is a bad default, and how a 117M-parameter encoder can cover both short structural tasks and arbitrarily long sequences.
Can Fine-Tuned Vision-Language Models Generalize Across Tasks on the Same Images?
Published:
A small experiment on whether fine-tuning a vision-language model for one visual task helps it handle other tasks on the same images.