CV
Last updated on December, 2025.
General Information
| Name | Rebati Gaire |
| [email protected] | |
| Location | Lincoln, NE, USA |
| linkedin.com/in/rrgaire | |
| GitHub | github.com/rrgaire |
| Google Scholar | rebatigaire |
Education
-
2023.01 - 2024.12 MS in Computer Science
University of Nebraska-Lincoln, Lincoln, NE, USA
- Awards - Outstanding Master’s Thesis Award 2025, Most Improved Master's Student 2024
- Courses - Design and Analysis of Algorithm, Design and Analysis of Efficient Algorithm (Advanced), Introduction to Deep Learning, Advanced Software Engineering, Computer Architecture, Hardware-Software Acceleration for Machine Learning
-
2016.11 - 2021.04 BE in Computer Engineering
Tribhuvan University, IOE, Pulchowk Campus
- Award - Merit-based scholarship for undergraduate studies
- Courses - Computer Programming in C, Object Oriented Programming with C++, Theory of Computation, Data Structure and Algorithm, Discrete Mathematics, Calculus-I, Calculus-II, Probability and Statistics, Object Oriented Analysis and Design, Artificial Intelligence, Database Management System, Distributed System, Computer Networks and Security, Digital Signal Analysis and Processing, Simulation and Modeling, Internet and Intranet, Information System
Experiences
-
2024.02 - Present Chicago, IL, USA
Machine Learning Engineer
University of Illinois Chicago
- Brainstorming, developing, and implementing novel machine learning algorithms optimized for hardware applications, focusing on energy efficiency and computational performance.
- Managing and analyzing datasets, preparing data for experiments, and ensuring data integrity for research studies.
- Maintaining and troubleshooting hardware setups and software environments for machine learning projects.
- Assisting in writing research proposals, grant requests, manuscript preparation, and presentations.
-
2023.01 - 2024.12 Lincoln, NE, USA
Graduate Research Assistant
School of Computing, UNL
- Led pioneering research on compressing deep learning models with integrated active learning, achieving a notable improvement in accuracy of 3.62% while reducing up to 40% labeled training samples
- Achieved a 5X reduction in computation and inference latency with the proposed compression technique, ensuring the delivery of robust and scalable solutions for edge devices.
- Published and presented research at peer-reviewed journals and conferences including ICMLA 2023 and TETC 2024.
-
2021.04 - 2022.12 Kathmandu, Nepal
Computer Vision Research Engineer
NAAMII
- Secured first place in the EndoVis FetReg challenge at MICCAI 2021, with a novel self-supervised medical image segmentation framework, improving the performance of UNet and U2Net by 2.5%.
- Successfully collaborated with multiple researchers on pioneering research in advanced deep federated learning techniques for cross-domain surgical image segmentation.
- Published research in the Medical Image Analysis Journal and CVPR 2022 Conference.
-
2021.04 - 2022.12 London, UK
Machine Learning Engineer - Computer Vision
Redev Technology
- Orchestrated the implementation of contemporary Active Learning pipelines, integrating cutting-edge algorithms such as Coreset, Learning Loss, and Vision transformer, resulting in a remarkable reduction of up to 30% in annotation costs for computer vision tasks.
- Spearheaded the development of a comprehensive deep learning system covering all stages from data collection, annotation, processing, training to evaluation, facilitating smart city initiatives by enabling robust detection of persons and vehicles, smoke and fire across diverse environmental conditions, including varying geography, occlusion, lighting, and weather scenarios.
-
2020.06 - 2020.09 Lalitpur, Nepal
AWS AI/ML Interestship
Genese Cloud Academy
- Gained proficiency in utilizing diverse AWS services including EC2, S3, Lambda, Sagemaker, Lex, Rekognition, and Polly.
- Successfully executed machine learning assignments and projects utilizing AWS services.
-
2019.05 - 2019.11 Lalitpur, Nepal
Software Developer Intern
UBL R&D Center
- Engineered and deployed a robust user management platform integrated with the PostgreSQL database for a full-stack web application for an innovative image annotation tool.
Publications
-
2025 CARN - Complexity-Aware Routing Network for Efficient and Adaptive Inference
Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)
-
2025 FDAL - Leveraging Feature Distillation for Efficient and Task-Aware Active Learning
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)
-
2024 Resource-Efficient Adaptive-Network Inference Framework with Knowledge Distillation-Based Unified Learning
2024 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)
-
2024 DECO - Dynamic Energy-aware Compression and Optimization for In-Memory Neural Networks
2024 IEEE 67th International Midwest Symposium on Circuits and Systems (MWSCAS)
-
2024 APRIS - Approximate Processing ReRAM In-Sensor Architecture Enabling Artificial-Intelligence-Powered Edge
IEEE Transactions on Emerging Topics in Computing (TETC)
-
2023 SenTer - A reconfigurable processing-in-sensor architecture enabling efficient ternary MLP
Proceedings of the Great Lakes Symposium on VLSI 2023 (GLSVLSI)
-
2023 A client-server deep federated learning for cross-domain surgical image segmentation
MICCAI Workshop on Data Engineering in Medical Imaging (DEMI MICCAI)
-
2023 Placental vessel segmentation and registration in fetoscopy - literature review and MICCAI FetReg2021 challenge findings
Medical Image Analysis Journal (MedIA)
-
2023 Why is the winner the best?
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
-
2023 Histogram of oriented gradients meet deep learning - A novel multi-task deep network for 2D surgical image semantic segmentation
Medical Image Analysis Journal (MedIA)
-
2023 EnCoDe - Enhancing Compressed Deep Learning Models Through Feature Distillation and Informative Sample Selection
2023 International Conference on Machine Learning and Applications (ICMLA)
-
2022 GAN-Based Two-Step Pipeline for Real-World Image Super-Resolution
ICT with Intelligent Applications - Proceedings of ICTIS 2021
Skills
| Programming Languages | |
| Python | |
| JavaScript | |
| C/C++ | |
| SQL | |
| Matlab |
| Web Frameworks | |
| Django | |
| Flask | |
| ReactJS | |
| NodeJS |
| ML & DL Libraries | |
| PyTorch | |
| TensorFlow | |
| Keras | |
| Scikit-Learn | |
| OpenCV | |
| Pandas | |
| NumPy | |
| SciPy | |
| NLTK |
| MLOps & Deployment | |
| Docker | |
| Kubernetes | |
| MLflow | |
| Apache Airflow | |
| AWS SageMaker | |
| Model Serving |
| LLM Inference & Serving | |
| LLMOps | |
| RAG | |
| Ollama | |
| vLLM | |
| FAISS | |
| Semantic Search | |
| Tree-sitter |
| Tools & Platforms | |
| AWS | |
| Linux | |
| Git | |
| Roboflow | |
| LaTeX | |
| WandB | |
| Matplotlib | |
| Seaborn |
Open Source Projects
- 2025
SourceLens; LLM-Powered Codebase Navigator
A semantic code exploration tool to accelerate large-scale codebase understanding using CodeBERT embeddings, Tree-sitter parsing, FAISS indexing, and retrieval-augmented prompting.
- 2022
ClauseAI; LLM-Based Contract Risk Analyzer
A Dockerized full-stack application for clause-level contract risk analysis using local LLM inference (Llama 3.1), FAISS-based semantic retrieval over the CUAD dataset, and RAG via a FastAPI backend and ReactJS frontend.
- 2021
SuperRes.AI; Real-World Image Super-Resolution with GANs
A production-ready image enhancement pipeline combining Real-ESRGAN and GFPGAN models in a Dockerized FastAPI service with ReactJS frontend for scalable real-world photo restoration.
- 2023
EnCoDe
EnCoDe merges active learning, model compression, and knowledge distillation to optimize deep learning models for edge devices. This technique addresses issues such as generalization loss, resource intensity, and data redundancy that often affect compressed models.
- 2022
Medical Image Segmentation
Winner of the FetReg 2021 challenge at MICCAI 2021 that uses a novel deep multi-task learning method for medical image segmentation leveraging Histogram of Oriented Gradients (HOGs) to generate pseudo-labels.
- 2021
Real-ImageSR
A GAN-based two step pipeline for enhancing the resolution of real-word low resolution image by the scale factor of 4. First, the R2B generator transforms real-world LR images to bicubic alike images. Then the nESRGAN+ network super-scales the output of the R2B generator.
- 2021
Image Super-Resolution
A full-stack web app to serve the GAN-based real-image super-resolution model using ReactJS, Flask and Tensorflow Serving with Docker
- 2021
Graduate Program Management
A Django-based web application to automate the document creation and management of MSC thesis programs in DOECE, IOE, Pulchowk Campus with a centralized PostgreSQL database fro managing records of the program, students, and faculties.