WiFi-Radar uses commodity WiFi routers to capture Channel State Information (CSI) data, which contains phase and amplitude information of WiFi signals. By analyzing how these signals reflect off human bodies, our system can detect human presence, estimate poses, and track movements - even through walls.

A comprehensive toolkit for developing and benchmarking compression algorithms specifically designed for neural data streams in brain-computer interfaces (BCIs). This project provides efficient, real-time compression solutions that preserve the critical characteristics

EEG-RAG is a Retrieval-Augmented Generation (RAG) system specifically designed for electroencephalography (EEG) research. It enables researchers, clinicians, and data scientists to ask natural language questions about EEG literature and receive evidence-based answers with proper citations.

(NeurIPS 2025), Compact CNNs for EEG decoding: response time prediction and behavioral assessment using competition starter kit infrastructure with custom normalization and training strategies using the Healthy Brain Network (HBN) EEG dataset

This project demonstrates a comprehensive machine learning pipeline with examples of supervised, unsupervised, and semi-supervised learning approaches. It serves as a template and learning resource for ML practitioners.

This project implements a deep learning pipeline for tumor detection and segmentation in medical images (MRI/CT) using the MONAI framework and PyTorch.

An optimized implementation of the Kimi Linear architecture - a hybrid linear attention mechanism outperforming traditional full attention.

A comprehensive industrial automation platform demonstrating integration between machine vision systems, industrial robots, PLCs, and quality control systems for modern manufacturing applications.

Brain-Forge is an advanced brain-computer interface system that combines cutting-edge neuroimaging technologies to create comprehensive brain scanning, mapping, and simulation capabilities. The platform integrates multi-modal sensor fusion, real-time data processing, and neural simulation to enable unprecedented understanding and modeling of brain

A project to build GPU acceleration for LLaMA models on local computers and AWS, leveraging GPU resources for efficient inference and training.

An AI-powered system for analyzing James Webb Space Telescope images to identify artificial structures, Dyson spheres, and objects that don't follow standard gravitational rules - potential indicators of intelligent extraterrestrial life.

The Internet of Space Things (IoST) is a revolutionary platform that brings Internet of Things (IoT) concepts to space exploration, specifically designed to support human spaceflight missions. This project creates an intelligent, interconnected ecosystem of sensors, communication systems, and AI-driven analytics to ensure crew safety,

This repository contains experimental quantum computing algorithms and simulations for cutting-edge research applications including medical genomics, cosmology, and quantum machine learning.

Lightweight, extensible Brownian dynamics toolkit for nanoparticles and proto-nanorobotics NanoSimLab provides accessible tools for simulating and analyzing nanoparticle systems using Brownian dynamics, with a focus on nanorobotics research and development. The toolkit runs out-of-the-box with NumPy/SciPy and offers seamless integration.

AdaAttn is a GPU-native attention mechanism that dynamically adapts both numerical precision and matrix rank at runtime, reducing memory bandwidth and computational overhead in large language models without sacrificing model quality. By aligning linear algebra operations with modern GPU hardware characteristics.

Professional development environment for PySpark ETL interviews and practice.

A comprehensive Python-based machine learning platform for real-time seismic event detection, analysis, and classification. This system integrates with authoritative seismic data sources (USGS and IRIS) to provide intelligent earthquake monitoring and analysis capabilities.

A specialized compression and interface layer that enables Apple's BCI HID technology to work more efficiently with existing BCI compression algorithms, focusing on low latency and high signal quality.

QuantumForge is an open-source framework that revolutionizes quantum chemistry calculations by combining the power of GPU acceleration, deep learning, and density functional theory. Built for researchers who demand both accuracy and performance.

GPU-Accelerated Brain Image Processing Pipeline for OpenNeuro Datasets