Naimul Haque
PhD Student & Researcher

Naimul Haque

Entrepreneur · Computer Vision · LLMs · Trustworthy AI
PhD Student & Graduate Research Assistant
School of Electrical Engineering & Computer Science
Louisiana State University (LSU), Baton Rouge, LA
Founder @ Gradmate.ai
naimul@gradmate.ai nhaque4@lsu.edu +1 (607) 454-1231 Baton Rouge, LA 70803

01 About

I am a PhD student and Graduate Research Assistant at Louisiana State University (LSU), where my research sits at the intersection of computer vision, large language models, and multimodal AI. My current doctoral work focuses on privacy-preserving face-swapping pipelines — transferring facial identity while formally protecting sensitive biometric attributes — directly contributing to Trustworthy AI and data privacy research.

In parallel, I am the founder of Gradmate.ai — an AI-powered platform streamlining graduate school applications through LLM orchestration, semantic program matching, SOP generation, and IELTS practice. Prior to LSU, I was a Graduate Research Assistant at Alfred University, where I won 1st place (tied) in the Advizex AI Innovation Challenge, developed an AI sales bot projected to increase ROI by 25%.

My publication record spans IEEE conferences, ICPR, and arXiv, with work in facial attribute captioning, sign-language recognition, low-resolution license plate recognition, and toxic content classification. I also have open datasets and fine-tuned models on HuggingFace actively used by the community.

6+
Publications
4.0
MSc GPA
5+
Years Teaching
1st
Advizex AI Prize
02 Research Interests
Trustworthy AI Privacy-Preserving AI Computer Vision Face Analysis & Synthesis Large Language Models Catastrophic Forgetting Agentic AI & Multi-Agent Systems Representation Learning Multimodal Systems GAN & Diffusion Models NLP / Transformers Continual Learning Reinforcement Learning AI for Finance & Banking AI for Energy Systems Image Captioning
03 Selected Projects
PhD Research · Trustworthy AI · Current
Privacy-Preserving Face-Swapping Pipeline

Current PhD research developing a face-swapping pipeline that transfers facial identity while formally protecting sensitive biometric attributes from inference attacks. Directly contributing to Trustworthy AI and data privacy, with techniques for identity disentanglement in generative models enabling controlled face synthesis with formal privacy guarantees.

Current Work Trustworthy AI Privacy Face Swapping Biometric Privacy
W-Space Refined Face Swapping Pipeline
Computer Vision · Generative AI
Neural Facial Identity Disentanglement via W-Space Refined StyleGAN Swapping

A face-swapping pipeline disentangling facial identity from expression and appearance in StyleGAN's W-space. Introduces DeepFace neutral-emotion filtering to source neutral-expression StyleGAN faces, paired with InsightFace gender validation for controlled attribute transfer. W-Space Refined blending outperforms Hybrid fusion (ID↔Src cosine similarity 0.359 vs. 0.232), enabled by convex-hull face masks from 106 landmarks, fixed Poisson blending with ROI boundary clamping, and pre-blend colour correction.

StyleGAN DeepFace InsightFace Poisson Blending W-Space Face Disentanglement
FaceGemma Portrait Captioning Results
Computer Vision · Image Captioning · ICPR 2024
FaceGemma: Attribute-Aware Portrait Image Captioning

FaceGemma enhances a Gemma-based vision-language model with an explicit facial attribute encoder, producing rich, identity-aware captions for portrait images. Trained on the custom FaceAttDB multilingual dataset (Zenodo), the model improves BLEU and CIDEr metrics over general-purpose captioners by conditioning generation on age, gender, emotion, and facial geometry.

Gemma VLM Facial Attributes Image Captioning FaceAttDB ICPR 2024
Research · LLM · Continual Learning · ACL ARR
Catastrophic Forgetting in LLMs: Sequential Fine-Tuning on NLP Benchmarks

Systematic empirical analysis of how LLMs degrade on previously learned NLP tasks after sequential domain fine-tuning. Benchmarks span GLUE tasks (SST-2, MRPC, CoLA, MNLI) across sub-10B open-weight models (Orca, Qwen). Explores elastic weight consolidation, LoRA merging, and replay strategies as mitigation techniques. Identified models with minimal forgetting for robust continual learning. Under review at ACL ARR 2024.

Continual Learning GLUE / SuperGLUE LoRA EWC Orca · Qwen
Entrepreneurship · NLP · LLM Systems
Gradmate.ai — AI Copilot for Graduate School Applications

Founded and engineered Gradmate.ai, an end-to-end LLM-powered platform for graduate applicants. Core features include semantic program discovery (dense retrieval over university programme embeddings), multi-agent SOP/LOR generation via LangGraph, IELTS adaptive practice, and a community knowledge base. Stack: LangChain · LangGraph · Groq · DeepSeek · Next.js. Seeking seed investment to scale.

LangChain LangGraph Groq RAG Multi-Agent EdTech
Agentic AI · Kaggle
Multi-Agent LLM System (Gemma / Kaggle)

Implemented a three-agent system using Gemma LLMs for Kaggle data tasks: Agent-1 (prompt generation), Agent-2 (context retrieval & elaboration), Agent-3 (suggestion synthesis). Backed by TensorFlow, PyTorch, and JAX. Also developed a reflection-based prompt engineering technique using Llama 3.1 for the LLM 20 Questions competition.

Gemma Multi-Agent JAX PyTorch Prompt Engineering
PhD Thesis · LLM × Energy Systems
AI Copilot for GE Vernova GridOS: LLM-Driven Smart Grid Management

Doctoral thesis developing a multi-agent LLM system integrated with GE Vernova's GridOS platform for real-time power grid decision support. Agents handle fault diagnosis, load-balancing recommendations, and operator-alert summarisation using LangChain tool-calling over ADMS/AEMS APIs. Evaluated against operator response latency and decision-accuracy benchmarks.

LangChain Groq ADMS · AEMS Power Systems GE Vernova
NSF Research · Physics-Informed ML
AI-Driven Battery Material Discovery (NSF Project)

NSF-funded summer research applying physics-informed neural networks to predict battery performance metrics including energy density and fast-charging rates. Explored AI-driven material discovery workflows to accelerate next-generation battery development.

Physics-Informed NN Material Science NSF PyTorch
Computer Vision · Infrastructure Safety
Power Line Fault Detection via Vision-Language Model

Leveraged Phi-3 Vision to analyze thermal and RGB power line imagery, detecting rust, hot spots, and flashover damage for infrastructure safety optimization. Demonstrates multimodal AI applied to critical energy infrastructure inspection workflows.

Phi-3 Vision VLM Thermal Imaging Infrastructure
Bangla License Plate Recognition
Computer Vision · OCR · IEEE
Automatic Bangla License Plate Recognition for Low-Resolution Imagery

A two-stage deep-learning pipeline for recognising Bangla license plates under real-world low-resolution conditions. YOLO-based detector localises the plate region, followed by a CNN-LSTM sequence model for character recognition. Evaluated on a custom surveillance dataset achieving state-of-the-art accuracy for Bangla script.

YOLOv8 CNN-LSTM OCR Bangla Script IEEE STI 2022
Computer Vision · Human-Computer Interaction
BdSpell: Real-Time Bangla Finger-Spelling Recognition via YOLO

A real-time Bangla Sign Language finger-spelling system built on a custom-trained YOLOv8 object detector operating at 30+ FPS on commodity hardware. Curated dataset of 36 Bangla hand-gesture classes under varied lighting and background conditions, achieving 94.3% mAP. Published at ICRIC 2023.

YOLOv8 Sign Language Real-Time Bangla NLP ICRIC 2023
Portrait Colorization Results
Computer Vision · Generative · IEEE ICCIT
Grayscale Portrait Colorization via CNN and Pretrained VGG-Face Descriptors

An automatic portrait colorization framework leveraging identity-aware features extracted from a pretrained VGG-Face network as conditioning signals for a CNN colorization decoder. By anchoring colour prediction to facial identity features, the model produces perceptually plausible skin-tone and hair-colour outputs consistent across different images of the same subject.

CNN VGG-Face Colorization Portrait IEEE ICCIT 2019
04 Publications
2024 Under Review
Catastrophic Forgetting in LLMs: A Comparative Analysis Across Language Tasks
Naimul Haque
ACL ARR 2024
2024 ICPR
FaceGemma: Enhancing Image Captioning with Facial Attributes for Portrait Images
Naimul Haque, Iffat Labiba, Sadia Akter
International Conference on Pattern Recognition (ICPR 2024)
2023 ICRIC
BdSpell: A YOLO-based Real-time Finger Spelling System for Bangla Sign Language
Naimul Haque, Meraj Serker, Tariq Bin Bashar
ICRIC 2023 — International Conference on Recent Innovations in Computing
2022 IEEE
Bangla Toxic Comment Classification and Severity Measure Using Deep Learning
Naimul Haque, Md. Bodrul, Abdullah, Towfiq, Mehorab
ICRPSET 2022 — International Conference on Recent Progresses in Science, Engineering and Technology
2022 IEEE
Automatic Bangla License Plate Recognition System for Low-Resolution Images
Naimul Haque, Samira Islam, Rabeiya Afrose, Mohammad Shorif Uddin
IEEE STI 2022 — 4th International Conference on Sustainable Technologies for Industry 4.0
2019 IEEE
Grayscale Portrait Colorization using CNNs and Pretrained VGG-Face Descriptor
Naimul Haque, Samin Shahriar Tokey
IEEE ICCIT 2019 — 22nd International Conference on Computer and Information Technology
Datasets & Models
2022 Zenodo
Bangla License Plate Dataset 2.5k
Naimul Haque et al.
Zenodo — 2022
2023 Zenodo
FaceAttDB: A Multilingual Dataset for Facial Attribute Captioning
Naimul Haque, Abida Sultana
Zenodo — June 2023
2023 HF
Bangla Toxic Comments Database
Naimul Haque, Badrul
HuggingFace Datasets — June 2023
2024 HF
GlueOrca & GlueQwen: Fine-tuned Models for GLUE Benchmark Tasks
Naimul Haque
HuggingFace Model Repository
05 Experience
Jan 2026 – Present
Graduate Research Assistant & PhD Student
Louisiana State University (LSU)
Privacy-preserving face analysis, identity disentanglement in generative models, and AI for smart energy grids.
  • Developing privacy-preserving face-swapping pipeline — Trustworthy AI contribution
  • Sequential fine-tuning experiments on GLUE/SuperGLUE benchmarks
  • LLM copilot system for GE Vernova GridOS (thesis)
Nov 2024 – Present
Founder & Chief Technology Officer
Gradmate Inc. / Gradmate.ai
Founded and lead development of an AI-powered graduate application platform.
  • LangChain & LangGraph for multi-agent LLM orchestration
  • Groq and DeepSeek for low-latency LLM inference
  • RAG-based program discovery and SOP generation pipelines
  • System architecture, model deployment, scalability
Summer 2025
Battery Machine Learning Researcher
NSF-Funded Project, Alfred University
Applied physics-informed neural networks to predict battery performance metrics (energy density, fast-charging rates) for AI-driven material discovery.
Summer 2025
Summer Research Director
Alfred University — Undergrad Summer Research Program
Directed undergraduate interdisciplinary research projects; provided mentorship on experimental design, data analysis, and project execution.
Summer 2025
Summer Internship Fellow
Institute for Experiential Entrepreneurship, Alfred University
Contributed to AI-driven educational programs and mentored students integrating AI technologies into experiential learning frameworks.
Jan 2024 – Sep 2025
Graduate Assistant
Alfred University — Inamori School of Engineering
Taught and prepared labs for Microprocessor, Mechatronics, Engineering Design, and Python for Power Electronics. Guided students in microprocessor interfacing, mechatronics design, and Python-based simulations.
Aug – Dec 2023
Assistant Professor
Uttara University
Taught Discrete Mathematics, Data Structures, and Structured Programming.
Apr 2019 – Jul 2023
Senior Lecturer / Lecturer
Manarat International University & Cognition.AI Lab
Delivered AI, Computer Vision & Robotics, Neural Networks & Fuzzy Systems, Pattern Recognition, Algorithm, Microprocessor & Interfacing. Supervised capstone projects in face recognition and object detection.
06 Education
2026 – Present
Ph.D. — Electrical Engineering & Computer Science
Louisiana State University (LSU)
Baton Rouge, LA
Jan 2024 – Dec 2025
M.Sc. — Electrical Engineering
Alfred University
Alfred, NY
GPA 4.0 / 4.0
2019 – 2022
M.Sc. — Computer Science
Jahangirnagar University
Bangladesh
GPA 3.53 / 4.0
2014 – 2018
B.Sc. — Computer Science & Engineering
Ahsanullah University of Science & Technology (AUST)
Bangladesh
GPA 3.71 / 4.0
07 Technical Skills
Languages
Python (Expert) · R · C/C++ · MATLAB · JavaScript · Linux/Unix
CV Frameworks
OpenCV · YOLOv8 · Detectron2 · DLIB · SAM · Landmark Detection
Generative / Face
StyleGAN · DeepFace · InsightFace · Diffusers · GANs · Diffusion Models
ML / DL
PyTorch · TensorFlow · Keras · JAX · Scikit-learn · CNNs
NLP / LLM
HuggingFace · LangChain · LangGraph · Transformers · LoRA · RAG
Inference
Groq · DeepSeek · Ollama · vLLM · Multi-Agent Systems
MLOps / Tools
Docker · Git · Google Cloud · Weights & Biases · Unity · LaTeX
Power Systems
GE ADMS · AEMS · GridOS · Power Analytics
08 Awards & Recognition
1st Place (Tied) — Advizex AI Innovation Challenge · 2024
Built an AI sales bot using Llama & LangChain, projected to increase ROI by 25%. Featured in Alfred University Press Release, May 2025.
EPRI Certification — Machine Vision in the Electric Industry with Deep Learning · Aug 2024
22 PDHs in Power Industry AI applications.
1st Position — Inter-University ADEX Engenius 2017 Software Development Competition
Team Telapoka.
2nd Position — Techfiesta 17 Software Development Competition
Team Telapoka.
1st Position — Intra-AUST Project Show, CSE Software Development Competition
Team Z Warriors.
09 References
Reference 1
Dr. Xingwu Wang
Professor of Electrical Engineering
Alfred University
fwangx@alfred.edu · (607) 871-2548
Reference 2
Dr. Kun Wang
Associate Professor, Material Science & Eng.
Alfred University
wang@alfred.edu · (607) 871-2729
Reference 3
Dr. Kazi A. Kalpoma
Professor, Dept. of CSE
Ahsanullah University of Science & Technology
kalpoma@aust.edu