My current research focuses on human-like virtual agents driven by large language models (LLMs), and their impact on human communication and training.

Research Experience: LLM alignment (DPO/RLHF), human-centric AI, synthetic data, ML for healthcare and code intelligence, and low-resource NLP.

Highlights

• [April 21, 2024] Public speaking, "Rethinking Capitalism in the Age of AGI" at ROC Talks Annual Event (Spring '24)! Video
• [Feb 15, 2024] Speaking about Future of Interactive Education with Generative AI at New York Academy of Sciences
• [Feb 21, 2024] Privacy, Security, Ethics of Generative AI, University of Rochester
• [Fall, 2023] I am talking about how generative AI is going to affect human connections on WXXI News radio show Connections with Evan Dawson. Link to the episode.

Show more highlights

• [Fall, 2023] My talk about our research got featured on University of Rochester news events.
• [Fall, 2023] Our work on virtual human based online education got featured in local TV News10NBC.
• [Fall, 2023] I am speaking about our research on LLM-driven virtual humans at Flower City AI conference in Rochester. Link to the talk.
• [Fall, 2023] Conducting a 4 part workshop series on Generative AI with Ain Center of Entrepreneurship, University of Rochester
• [Fall, 2023] Serving as a judge for Creative Collision Challenge, University of Rochester
• [Spring, 2023] Our team got featured in UofR News Center!
• [Spring, 2023] Conducting a workshop "Introduction to ChatGPT" with Ain Center of Entrepreneurship, University of Rochester
• [Spring, 2022] Serving as a reviewer for Late Breaking Work workshop at CHI 2022.
• [June 02, 2021] Text2App got featured in TechXplore. Text2App: A framework that creates Android apps from text descriptions

Publications

LLMs, Alignment, and Human-Like AI

• HAL: Inducing Human-likeness in LLMs with Alignment Masum Hasan, Junjie Zhao, Ehsan Hoque. [Under review]
• SAPIEN: Affective Virtual Agents Powered by Large Language Models Masum Hasan, Cengiz Ozel, Sammy Potter, Ehsan Hoque (ACIIW 2023) [arxiv]
• 'Poker with Play Money': Exploring Psychotherapist Training with Virtual Patients Cynthia M. Baseman Masum Hasan, Nathaniel Swinger, Sheila A. M. Rauch, Ehsan Hoque, Rosa I. Arriaga (CSCW 2025)

Human-Centered AI and Healthcare

• AI Standardized Patient Improves Human Conversations in Advanced Cancer Care Kurtis Haut, Masum Hasan, Thomas Carroll, Ronald Epstein, Taylan Sen, Ehsan Hoque [Under review]
• A User-Centered Framework to Empower People with Parkinson's Disease Wasifur Rahman, Abdelrahman Abdelkader, Sangwu Lee, Phillip Yang, Md Saiful Islam, Tariq Adnan, Masum Hasan, Ellen Wagner, Sooyong Park, E. Ray Dorsey, Catherine Schwartz, Karen Jaffe, Ehsan Hoque. (IMWUT, UbiComp 2024)
• Auto-Gait: Automatic Ataxia Risk Assessment with Computer Vision on Gait Task Videos. Wasifur Rahman, Masum Hasan, Md Saiful Islam, Titilayo Olubajo, Jeet Thaker, Abdelrahman Abdelkader, Phillip Yang, Tetsuo Ashizawa, Ehsan Hoque. (IMWUT, UbiComp 2023)

Synthetic Data and Computer Vision

• Hi5🤚: Synthetic Data for Inclusive, Robust, Hand Pose Estimation Masum Hasan, Cengiz Ozel, Nina Long, Alexander Martin, Samuel Potter, Tariq Adnan, Sangwu Lee, Amir Zadeh, Ehsan Hoque (ACII 2025)
• Hitting your MARQ: Multimodal ARgument Quality Assessment. Md Kamrul Hasan, James Spann, Masum Hasan Md. Saiful Islam, Kurtis Haut, Rada Mihalcea and Ehsan Hoque. (EMNLP 2021)

NLP for Code and Software Engineering

• CoDesc: A Large Code–Description Parallel Dataset. Masum Hasan, Tanveer Muttaqeen, Ishtiaq Niloy, Kazi Mehrab, Tahmid Hasan, Mahim Pantho, Wasi Uddin Ahmad, Rifat Shahriyar, Anindya Iqbal (ACL Findings 2021)
• Text2App: A Framework for Creating Android Apps from Text Descriptions. Masum Hasan, Kazi Sajeed Mehrab, Wasi Uddin Ahmad, Rifat Shahriyar. (NLP4Prog Workshop, ACL 2021)
• Review4Repair: Code Review Aided Automatic Program Repairing. Faria Huq, Masum Hasan, Mahim Pantho, Sazan Mahbub, Anindya Iqbal, Toufique Ahmed. (IST 2021)
• Using a Balanced Scorecard to Identify Opportunities to Improve Code Review Effectiveness: An Industrial Experience Report. Masum Hasan, Anindya Iqbal, Amiangshu Bosu, Mohammad Rafid Ul Islam, A.J.M. Imtiajur Rahman. (EMSE 2021)
• BERT2Code: Can Pretrained Language Models be Leveraged for Code Search? Abdullah Al Ishtiaq, Masum Hasan, Md. Mahim Anjum Haque, Kazi Sajeed Mehrab, Tanveer Muttaqueen, Tahmid Hasan, Anindya Iqbal, Rifat Shahriyar [Preprint]

Low-Resource NLP

• LowResource at BLP-2023 Task 2: Leveraging BanglaBert for Low Resource Sentiment Analysis of Bangla Language Aunabil Chakma, Masum Hasan (BLP Workshop, EMNLP 2023)
• Not Low-Resource Anymore: Aligner Ensembling, Batch Filtering, and New Datasets for Bengali-English Machine Translation.Tahmid Hasan, Abhik Bhattacharjee, Kazi Samin, Masum Hasan, Madhusudan Basak, M. Sohel Rahman, Rifat Shahriyar. (EMNLP 2020)
• Recognition of Bengali Handwritten Digits Using Convolutional Neural Network Architectures. Md Mahmudul Hasan, Md Rafid Ul Islam, Md Tareq Mahmood. (ICBSLP 2018)