Joyanta J. Mondal / জয়ন্ত মন্ডল
I’m a researcher from Dhaka, Bangladesh, with an M.S. in Computer Science from the University of Delaware.
My research focuses on efficient and trustworthy AI. I study how language models can be adapted and compressed with limited computation, and how to evaluate whether their predictions are reliable. This includes parameter-efficient fine-tuning, model pruning, and uncertainty estimation. I’m particularly interested in understanding the tradeoffs between efficiency and prediction quality. I’m also interested in reinforcement learning and how learning systems can use feedback to make decisions under uncertainty. I also work on computer vision and medical imaging, with a focus on models that can run with limited computing resources.
My works have been published in premium conferences and journals, including, Scientific Reports, Engineering Applications of Artificial Intelligence, EACL.
Outside research, I’m an avid gamer known as LePotatoGuy, a traveller, anime and comic enthusiast, cyclist, and a chess player rated around 400, which means I lose often and confidently. I’ve visited nearly half the U.S. states, and my Erdős number is 4. You can find more about me outside work.
News
- Nov 2026 PaperFlowNeg accepted to the Main Conference of EACL 2027 (Core A; 13.5% acceptance rate).
- Aug 2026 PaperReview Paper on Weakly Supervised 3D Pose Estimation published at Intelligent Systems with Applications
- Aug 2026 AwardAwarded Quality Journal Publication Award from BRAC University.
-
Dec 2025
DegreeCompleted M.S. in
Computer Science from the University of Delaware!
- Nov 2025 ReviewInvited as reviewer at PeerJ Journal.
Older news
- Aug 2025 Op-EdOp-Ed published in The Daily Star on responsible AI use in education. [Link]
- Jul 2025 PaperBAMPolyp (Mamba-based polyp segmentation) accepted at CVAMD @ ICCV 2025.
- May 2025 PaperTwo-step copyright-aware image generation model accepted at IFIP Summer School on Privacy and Identity Management.
- May 2025 AwardAwarded Quality Journal Publication Award from BRAC University.
- Apr 2025 PaperGCN+Transformer model for CB2 receptor ligand activity prediction accepted at IJCNN. [Link]
- Mar 2025 ReviewInvited as reviewer at NeurIPS 2025.
- Jan 2025 PaperAdversarial attacks paper (ET DeepFool) accepted at Scientific Reports.
- Dec 2024 FellowshipSelected for NSF-funded NRT-MIDAS fellowship program.
- Oct 2024 PaperInvolution Fused ConvNet for ASD eye-tracking classification accepted at EAAI.
- Aug 2024 EnrollmentStarted graduate studies at the University of Delaware.
- Feb 2023 Op-EdOp-Ed published in The Daily Star on ChatGPT in education. [Link]
Selected Publications
BAMPolyp: Bi-Axial Mamba Bottleneck for Gastrointestinal Polyp Segmentation
Tailoring Adversarial Attacks on Deep Neural Networks for Targeted Class Manipulation Using DeepFool Algorithm
Involution Fused Convolution for Classifying Eye-Tracking Patterns of Children with Autism Spectrum Disorder
Unmasking the Invisible: Finding Location-Specific Aggregated Air Quality Index with Smartphone-Captured Images
Sherlock in OSS: A Novel Approach of Content-Based Searching in Object Storage System
Orchestrating Image Retrieval and Storage over a Cloud System
PLeaD-Net: Identifying Plant Leaf Diseases through Leveraging Limited-Resource Deep Convolutional Neural Network
Honors & Awards
Quality Journal Publication Award
Quality Journal Publication Award
NRT-MIDAS Fellowship
NSF Research Support
Blazer Graduate Research Fellowship
Runner-Up, Best Research Poster Award
Travel & Participation Grant Fellowship
Reviewer Work
- Reviewer, NeurIPS 2025
- Reviewer, ICLR 2025 (13th)
- Reviewer, ACM CSCW 2024
- Judge, Undergraduate Research Expo, University of Alabama at Birmingham (Fall 2023)
- Reviewer, 1st WACV 2024 Workshop on Vision-Based Understanding for Low-Resource Languages (WVLL)
- Reviewer, ACM CHI 2024
- Reviewer, ICLR 2024 (12th)
- Reviewer, NeurIPS 2023
- Reviewer, NeurIPS 2024 Workshop on Foundation Model Interventions (MINT 2024)
- Reviewer, ACM Journal on Computing and Sustainable Societies
- Reviewer, PeerJ Journal
Skills
Education
M.S. in Computer Science
Graduate Studies (Transferred)
B.Sc. in Computer Science
Experience
Graduate Teaching Assistant @ University of Delaware
Blazer Graduate Research Fellow @ University of Alabama at Birmingham
Research & Teaching Assistant @ BRAC University
Courses: CSE472 (HCI), CSE474 (Simulation & Modeling), CSE484 (Cloud Computing)
Undergraduate Teaching Assistant @ BRAC University
Course: CSE474, Simulation and Modeling
Undergraduate Research Assistant @ BRAC University
Collaborations
My frequent collaborators include Dr. Ibne Farabi Shihab (Amazon), Meem Arafat Manab (phd researcher, Universidad Politécnica de Madrid, Spain), Md Farhadul Islam (phd researcher, Kentucky), Dr. Jannatun Noor (United International University, Bangladesh), and Dr. A. B. M. Alim Al Islam (BUET, Bangladesh).
Lineage
I am honored to be part of a distinguished academic lineage connecting to figures such as Isaac Newton, De Morgan, Thomson, and Rutherford.