Bishram Acharya

Bishram Acharya

Computer Engineering Graduate | AI Research Assistant
Computer Engineering graduate from Pulchowk Campus, Nepal, with research interests in vision language models. Currently pursuing research in AI with focus on practical applications in low resource settings. Connect with me

Education

BE in Computer Engineering
Pulchowk Campus, Institute of Engineering | 2021 - 2025
  • Achieved an aggregate of 79.57% over four years
  • Secured 80.79% in the final two years of study, with a strong focus on subjects like - Artificial Intelligence, Probability & Statistics, Applied Data Science, Simulation & Modeling , Software Engineering, Database Management Systems, Computer Organization & Architecture, Computer Graphics, Digital Signal Analysis & Processing
Higher Secondary Education, Physics
St. Xavier's College, Maitighar | 2018 - 2020
  • Physics Stream with GPA 3.79/4.0. Strong foundation in Mathematics and Physics' first principles thinking

Professional Experience

Research Assistant
NAAMII | June 2025 - Present
Research Intern
NAAMII | September 2024 - March 2024
  • Developed pipeline for ISIC skin lesion classification challenge
  • Reviewed literature at the intersection of Active Learning and Vision-Language Segmentation Models (VLSMs)
  • Critically analyzed an ongoing research paper, identifying key strengths and limitations, and proposed methodological improvements
  • Participated in regular reading sessions focused on understanding foundational deep learning concepts, especially through Chris Bishop’s Deep Learning Foundation and Concepts book
Freelance Developer
Upwork | 2023 - Present
  • Developed Python applications for automated news extraction and data scraping solutions
  • Performed web scraping, data processing, and automation tools for various clients

Research & Development

Academic research projects and practical development work

Research Projects

πŸ€–
AI Generated Image Detection
Deep learning approach for synthetic image identification

AI Generated Image Detection

Final year major project comparing frequency-based networks (FourierNet) with CLIP and custom SpectrCLIP model. Achieved F1 Score of 0.9877 and AUC 0.9993 with the best performing model.

Deep Learning Computer Vision CLIP PyTorch
πŸ‘†
Cross Platform Fingerprint Matching
CNN-based biometric authentication system

Cross Platform Fingerprint Matching Using CNN

Developed a Siamese network architecture using VGG-16 and DenseNet for fingerprint matching across different platforms. Achieved 89.2% accuracy in determining fingerprint matches.

CNN Siamese Networks Biometrics TensorFlow
🧬
Breast Cancer Histopathological Image Classification
A hybrid CNN-SVM model for classifying breast cancer histopathology images.

Breast Cancer Histopathological Image Classification

Developed a hybrid model combining Convolutional Neural Networks (CNN) for feature extraction and a Support Vector Machine (SVM) for classification of breast cancer histopathological images. This approach aims to improve diagnostic accuracy by leveraging the strengths of both deep learning and classical machine learning.

Deep Learning Computer Vision CNN SVM Medical Imaging
🏺
3D Reconstruction using Gaussian Splatting
Advanced 3D reconstruction technique for object modeling

3D Reconstruction using Gaussian Splatting

Implemented state-of-the-art 3D reconstruction using Gaussian Splatting technique for high-quality vase modeling. Created interactive 3D visualization demonstrating advanced computer vision and 3D modeling capabilities.

Computer Vision 3D Reconstruction Gaussian Splatting

Development Projects

πŸ“°
Automated News Extraction System
Python application for real-time news aggregation

Automated News Extraction System

Built a comprehensive Python application for automatic news extraction and display from skynews.au. Features real-time data processing, content filtering, and user-friendly interface for news consumption.

Python Web Scraping BeautifulSoup Automation
🏠
Real Estate Data Scraper
Comprehensive property data extraction tool

Real Estate Data Scraper

Developed a robust data scraping solution for real estate websites. Implemented advanced parsing techniques, data validation, and export functionality for market analysis and research purposes.

Python Data Mining Selenium Data Analysis
🌐
Portfolio Website
Responsive academic portfolio with modern design

Academic Portfolio Website

Designed and developed a clean, academic-focused portfolio website featuring responsive design, interactive project showcases, and optimized performance for professional presentation.

HTML/CSS JavaScript Responsive Design UI/UX

Technical Skills

Programming Languages

Python, C++, C, JavaScript

Machine Learning

PyTorch, TensorFlow, OpenCV, Scikit-learn

Data Science

Pandas, NumPy, Matplotlib, Data Analysis

Databases

MySQL, NoSQL, Data Management

Certifications & Achievements

Deep Learning Specialization
Coursera - Andrew Ng
Artificial Intelligence Course
Samsung Innovation Campus