Introduction

About Me

I am a fourth-year Ph.D. student in Computer Science at Oklahoma State University, where I work in the Reasoning and Artificial Intelligence (rAIson) Lab under the supervision of Dr. Atriya Sen. My research lies at the intersection of machine learning, deep learning, and natural language processing, with a focus on building efficient, interpretable, and reliable learning systems.

My current research focuses on memory-efficient language models, explainability in large language models, and representation learning. I am particularly interested in methods that analyze and improve how language models retain information, represent reasoning behavior, and use computational resources efficiently. My recent work explores directions such as low-rank token masking, adaptive memory retention, symbolic planning in transformers, and cross-modal reasoning.

Prior to beginning my Ph.D., I served as a Lecturer in the Department of Computer Science and Engineering at the University of Asia Pacific. In this role, I taught undergraduate computer science courses, including Machine Learning, Pattern Recognition, Algorithms, and Computer Graphics Lab, and mentored undergraduate research projects.

I earned my Bachelor of Science in Computer Science and Engineering from Rajshahi University of Engineering and Technology (RUET).

My long-term goal is to pursue an academic career that combines rigorous research, effective teaching, and sustained mentorship. I am broadly interested in developing machine learning methods that are not only technically strong but also interpretable, reproducible, and useful for real-world scientific and societal problems.

📄 Resume 🪪 CV 🐙 GitHub 🎓 Google Scholar 📚 DBLP 📖 Semantic Scholar 🆔 ORCID 💼 LinkedIn ✖️ X ✍️ Personal Blog


PhD Comics — The Research Cycle (Strip #1759)

“The Research Cycle” — Piled Higher and Deeper by Jorge Cham.
© Piled Higher and Deeper Publishing, LLC. Source

Highlights

Recent News


Education

INSTITUTES AND DEGREES

Ph.D. in Computer Science

Oklahoma State University Logo

Department of Computer Science

Oklahoma State University

August 2022 - Present

Bachelor of Science in Computer Science and Engineering

RUET Logo

Department of Computer Science and Engineering

Rajshahi University of Engineering and Technology

January 2012 - October 2016

Experience

Institutes and Duration

Oklahoma State University Logo

Graduate Teaching Assistant August 2022 - Present

Department of Computer Science, Oklahoma State University

Theory Courses:
  • Introduction to Computer Security (Fall 2022), Dr. Sharmin Jahan
  • Design and Implementation of Operating Systems I (Spring 2023, Spring 2024, Spring 2026), Dr. Shital Joshi
  • Data Structures and Algorithm Analysis II (Fall 2023), Dr. H. K. Dai
  • Discrete Mathematics for Computer Science (Fall 2024), Dr. Sachin Jain
  • Social Issues in Computing (Spring 2025), Dr. Rekha Bhowmik
  • Introduction to Database Systems (Fall 2025), Dr. Sadiq Albuhamood

Graduate Research Assistant May 2023 - August 2023, May 2025 - August 2025

Department of Computer Science, Oklahoma State University

  • Developed multimodal sentiment reasoning (ABSA/MABSA) models using aspect-aware fusion and attention alignment (text+image), and performed ablations to isolate the most critical components.
  • Investigated causal & robust multimodal reasoning by studying cross-modality alignment and feedback for real-time emotion understanding under missing/noisy modalities.
  • Built masking & optimization methods (contextual/syntax-guided masking; token-retention gating) to improve efficiency and memory/throughput, with fully reproducible pipelines and end-to-end profiling.
University of Asia Pacific Logo

Lecturer October 2018 - July 2022

University of Asia Pacific

Theory Courses:
  • Machine Learning (Spring 2020, Fall 2020)
  • Pattern Recognition (Fall 2018 - Fall 2019)
  • Algorithms (Fall 2020)
  • Mathematics for Computer Science (Spring 2021)
  • Visual and Web Programming (Fall 2021)
Lab Courses:
  • Computer Graphics Lab (Fall 2018 - Fall 2021)
  • Pattern Recognition Lab (Fall 2018 - Fall 2019)
  • Algorithms Lab (Fall 2019)
  • Compiler Lab (Fall 2020)
  • Object Oriented Programming II (Java) Lab (Spring 2021)
  • Visual and Web Programming Lab (Fall 2021)
Uttara University Logo

Lecturer February 2017 - October 2018

Uttara University

Theory Courses:
  • Programming Language and Application II (C++) (Fall 2017)
  • Operating System Design (Summer 2018)
  • Design and Analysis of Algorithms (Fall 2018)
  • Discrete Mathematics (Fall 2017)
Lab Courses:
  • Programming Language and Application II Lab (C++) (Fall 2017)
  • Operating System Design Lab (Summer 2018)
  • Design and Analysis of Algorithms Lab (Fall 2018)
Selected Publications

CONFERENCE PAPERS

(Most Recent First)
  1. MaskLoRA: Low-Rank Subspace–Induced Token Masking for Efficient and Faithful Language Models
    Rafiuddin, R. MaskLoRA: Low-Rank Subspace–Induced Token Masking for Efficient and Faithful Language Models. In Findings of the Association for Computational Linguistics: EACL 2026, March 24–29, 2026, Rabat, Morocco. Association for Computational Linguistics.
    Core A Conference Paper Presentation Poster Video
  2. Emergent Discrete Controller Modules for Symbolic Planning in Transformers
    Rafiuddin, S. M., & Khan, M. N. Emergent Discrete Controller Modules for Symbolic Planning in Transformers. In International Conference on Learning Representations (ICLR 2026), April 23–27, 2026, Riocentro Convention and Event Center, Rio de Janeiro, Brazil. Poster presentation.
    Core A* Conference Paper Presentation Poster Video
  3. A Formal Analysis of Chain-of-Thought Prompting via Turing Reductions
    Rafiuddin, S. M., and Khan, M. N. A Formal Analysis of Chain-of-Thought Prompting via Turing Reductions. In International Joint Conference on Natural Language Processing and Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP–AACL 2025), Short Papers. December 20–24, 2025 — Victor Menezes Convention Centre (VMCC), IIT Bombay, Mumbai, India.
    Core B Conference Paper
  4. A Detailed Factor Analysis for the Political Compass Test: Navigating Ideologies of Large Language Models
    Kamal, S., Prakash, L. P. Y., Rafiuddin, S. M., Rakib, M., Sen, A., & Ray Choudhury, S. A Detailed Factor Analysis for the Political Compass Test: Navigating Ideologies of Large Language Models. In International Joint Conference on Natural Language Processing & Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP–AACL 2025), Main Conference (Short). December 20–24, 2025 — Victor Menezes Convention Centre (VMCC), IIT Bombay, Mumbai, India.
    Core B Conference Paper
  5. Edu-EmotionNet: Cross-Modality Attention Alignment with Temporal Feedback Loops
    Rafiuddin, S. M. Edu-EmotionNet: Cross-Modality Attention Alignment with Temporal Feedback Loops. In Proceedings of the 24th International Conference on Machine Learning and Applications (ICMLA 2025), December 3–5, 2025, Boca Raton Marriott at Boca Center, Boca Raton, Florida, USA. Regular track. (Technically co-sponsored by IEEE; proceedings submitted to IEEE Xplore.)
    Core C Conference Paper Presentation
  6. Learning what to remember: Adaptive probabilistic memory retention for memory-efficient language models
    Rafiuddin, S. M., & Khan, M. N. Learning what to remember: Adaptive probabilistic memory retention for memory-efficient language models. In Findings of the Association for Computational Linguistics: Conference on Empirical Methods in Natural Language Processing (EMNLP) 2025 (Short). November 5–9, 2025 — Suzhou International Expo Centre (SuzhouExpo), Suzhou, China.
    Core A* Conference Paper
  7. AdaptiSent: Context-Aware Adaptive Attention for Multimodal Aspect-Based Sentiment Analysis
    Rafiuddin, S. M., Kamal, S., Rakib, M., Bagavathi, A., & Sen, A. (Forthcoming 2025). AdaptiSent: Context-Aware Adaptive Attention for Multimodal Aspect-Based Sentiment Analysis. In Proceedings of the 17th International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2025) (Short). August 25–28, 2025 — Embassy Suites, Niagara Falls, Ontario, Canada. (Acceptance Rate: ~25%)
    Core B Conference Paper Presentation
  8. PAKDD 2024 paper thumbnail
    Rafiuddin, S.M., Rakib, M., Kamal, S. and Bagavathi, A., 2024, April. Exploiting Adaptive Contextual Masking for Aspect-Based Sentiment Analysis. In Pacific-Asia Conference on Knowledge Discovery and Data Mining (pp. 147-159). Singapore: Springer Nature Singapore. (Acceptance Rate: 18.47%)
    Core B Conference Paper Presentation
  9. Isolated Bangla Handwritten Character Classification
    Karim, M. A., Rafiuddin, S. M., Islam Razin, M. J., & Alam, T. (2022, March). Isolated Bangla Handwritten Character Classification using Transfer Learning. In Proceedings of the 2nd International Conference on Computing Advancements (pp. 11-17).
    Paper
  10. High Cursive Complex Character Recognition
    Rafiuddin, S. M. (2022, March). High Cursive Complex Character Recognition using GAN External Classifier. In Proceedings of the 2nd International Conference on Computing Advancements (pp. 466-472).
    Paper
  11. LSTM Model for Business Sentiment Analysis
    Razin, J. I., Abdul Karim, M., Mridha, M. F., Rafiuddin Rifat, S. M., & Alam, T. (2021). A Long Short-Term Memory (LSTM) Model for Business Sentiment Analysis Based on Recurrent Neural Network. In Sustainable Communication Networks and Application (pp. 1-15). Springer, Singapore.
    Paper
  12. Estimation of Phylogenetic Tree using Gene Sequencing Data
    Rafiuddin, S. M. (2019, December). Estimation of Phylogenetic Tree using Gene Sequencing Data. Electrical Information and Communication Technology (EICT), 2019 4th International Conference on. IEEE, 2019.
    Paper
  13. Ranking of Bangla word graph using graph based ranking algorithms
    Rafiuddin, S. M. (2017, December). Ranking of Bangla word graph using graph based ranking algorithms. Electrical Information and Communication Technology (EICT), 2017 3rd International Conference on. IEEE, 2017.
    Paper
  14. Performance analysis of supervised machine learning algorithms for text classification
    Mishu, Sadia Zaman, and S. M. Rafiuddin (2016, December). Performance analysis of supervised machine learning algorithms for text classification. Computer and Information Technology (ICCIT), 2016 19th International Conference on. IEEE, 2016.
    Paper

My Works

RESEARCH AND PROJECT DOCUMENTATION

  • Estimating Influenza Cases using Numerical Methods and Machine Learning (2024).
    Compared traditional SVIR-based numerical solvers (Midpoint, RK4) with deep learning models (LSTM, CNN, FTA-LSTM) and Random Forest for predicting H1N1 outbreaks; Random Forest with direct forecast achieved the best accuracy on real-world data.
    GitHub
  • Adaptive Blockchain with Dynamic Difficulty and SJF Prioritization (2024).
    Designed a blockchain simulation with dynamic difficulty adjustment and Shortest Job First (SJF) prioritization using a minimum priority queue to improve throughput, reduce queue length, and lower waiting time under high transaction loads; developed as part of OSU’s CS5113 course.
    GitHub
  • Sentiment Analysis on Cloud Platforms (2022).
    Developed and compared sentiment analysis pipelines across AWS Comprehend, Google Cloud NLP, and IBM Watson to evaluate API-based NLP sentiment classification on real-world datasets.
    GitHub
  • GO-CART – 3D Unity Game (2021).
    Designed a Unity-based 3D racing game with smooth player movement (W/A/S/D), third-person camera tracking, and physics-based controls. The game features real-time scoring, collision detection, and a game over system triggered on crash or completion.
    GitHub
  • Breast Cancer Detection using Deep Learning (2021).
    Built multiple CNN-based models including Inception, VGG16, MobileNet, and Transformers to detect Invasive Ductal Carcinoma (IDC) in histopathology images; evaluated on Kaggle's IDC dataset.
    GitHub
  • Image Embedding with Classification by Deep Neural Networks (2021).
    Developed a deep learning pipeline using Xception to extract and visualize image embeddings for classification tasks. Includes TensorBoard-based 2D/3D demo.
    GitHub Paper
  • Data Augmentation with Generative Adversarial Networks (2021).
    Implements adaptive discriminator augmentation to stabilize GAN training on limited datasets, supporting Bangla character/numeral synthesis and multiple architectures. Includes demo visualization.
    GitHub Demo
  • Protein Structure Prediction using PyRosetta (2020).
    Developed molecular modeling pipelines using PyRosetta for protein structure prediction and refinement as part of my graduate thesis.
    GitHub
  • Phylogenetic Tree Construction with Genetic Algorithms (2019).
    Applied genetic algorithms for evolutionary tree estimation using gene sequencing data; includes modular support for multiple genome datasets from NCBI.
    GitHub Paper
  • Performance Analysis of Text Classification in NLP with Supervised Machine Learning Algorithms (2016).
    Evaluated various supervised models including ANN with Backpropagation for classifying labeled text datasets; conducted as undergraduate thesis work.
    GitHub Paper
  • Java Scientific Calculator (2014).
    Built a desktop-based scientific calculator using Java Swing, featuring basic arithmetic, trigonometric, logarithmic, and exponential functions with keyboard and GUI input support.
    GitHub
Misc Links

WEBLINKS





Get in Touch

Contact

where.is.rifat@gmail.com

Stillwater, Oklahoma, USA