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.

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

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

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.

WACV 2026 RWS Challenge: Building object detectors that maintain consistent performance across seasons, weather patterns, and day-night cycles in thermal imagery.

ALS Research Literature RAG System - FAISS + sentence-transformers + OpenAI

This project implements PDDL-INSTRUCT with Logical Chain-of-Thought (LCoT), a novel approach to improve Large Language Model (LLM) performance on automated planning tasks. The system enhances planning capabilities through:

An intelligent research assistant powered by LangChain and Claude that helps neuroscience researchers query neural datasets, generate summaries, and plan experiments.

A comprehensive implementation of Nvidia NeMo Guardrails for AI safety and responsible AI development.