Jules Udahemuka (realjules)

realjules

User data from Github https://github.com/realjules

0

followers

0

following

0

stars

Company:CMU'25 | Engineering AI

Home Page:https://realjules.github.io/

GitHub:@realjules

Twitter:@udaheju

Jules Udahemuka's repositories

africa_climate_simulation

The Digital Twin for Climate Resilience in Africa project addresses the challenges of fragmented climate data in Africa. Focusing on Rwanda, it integrates data to create a virtual replica of the climate system, enabling better understanding, prediction, and adaptation to climate change impacts.

Language:PythonLicense:NOASSERTIONStargazers:0Issues:0Issues:0

ai-podcast-cohost

An interactive AI-powered podcast co-host with voice interaction and document processing capabilities

Language:HTMLLicense:MITStargazers:0Issues:0Issues:0

align_llm

The LLM Defense Framework enhances large language model security through post-processing defenses and statistical guarantees based on one-class SVM. It combines advanced sampling methods with adaptive policy updates and comprehensive evaluation metrics, providing researchers and practitioners with tools to build more secure AI systems.

Language:PythonStargazers:0Issues:0Issues:0
Stargazers:0Issues:0Issues:0
Language:Jupyter NotebookStargazers:0Issues:0Issues:0
Language:PythonLicense:MITStargazers:0Issues:0Issues:0
Language:Jupyter NotebookStargazers:0Issues:0Issues:0
Language:C++Stargazers:0Issues:0Issues:0

monitor.ai

monitor.ai: Non-intrusive monitoring for FDA-approved medical AI, helping healthcare organizations ensure safety and compliance without modifying validated models.

Language:Jupyter NotebookStargazers:0Issues:0Issues:0
Language:PythonStargazers:0Issues:0Issues:0
Language:HTMLStargazers:0Issues:0Issues:0
Stargazers:0Issues:0Issues:0
Stargazers:0Issues:0Issues:0
Language:HTMLLicense:MITStargazers:0Issues:0Issues:0

resnet-classification

A face recognition and verification system implementing ResNet architectures (18-152) with PyTorch. Features comprehensive data augmentation, Weights & Biases integration, and a structured pipeline for both classification and similarity tasks.

Language:PythonStargazers:0Issues:0Issues:0

robdog-vision

Robot Vision Demo provides depth-based navigation for robots using DepthAnything, processing camera feeds to generate structured navigation commands. The system analyzes depth data across image regions, detects objects, and visualizes results through a responsive web interface for real-time monitoring and control.

Language:PythonStargazers:0Issues:0Issues:0

ScholarLens

ScholarLens analyzes research papers using RAG with AI models from OpenAI, Anthropic, and Google. It identifies research gaps, assesses novelty, extracts key concepts, visualizes citations, and enables natural language queries of academic content. Features include PDF processing, arXiv/Semantic Scholar integration, batch processing, and intelligent

Language:PythonStargazers:0Issues:0Issues:0
Stargazers:0Issues:0Issues:0

seq-to-seq

Training seq-to-seq LSTM

Language:PythonStargazers:0Issues:0Issues:0

speech-mlp

mlp for speech recognition

Language:PythonStargazers:0Issues:0Issues:0
Stargazers:0Issues:0Issues:0
Language:Jupyter NotebookStargazers:0Issues:0Issues:0