GitHub

E2D2: Encoder-Decoder Diffusion Language Models for Efficient Training and Inference

This repository contains code and scripts for reproducing experimental results from our work. We will try to use GitHub issues to track bugs, features, and todos. To contribute to the repo, please ...
IEEE

Wi-Fi-Based Human Fall and Activity Recognition Using Transformer-Based Encoder–Decoder and Graph Neural Networks

Abstract: Human pose estimation and action recognition have received attention due to their critical roles in healthcare monitoring, rehabilitation, and assistive technologies. In this study, we ...
GitHub

Multimodal Clinical RAG Assistant (Medical Text + Image Retrieval System)

This project addresses the "Modality Gap" in medical AI. Standard RAG systems are text-blind; they cannot "see" the X-Ray or Skin Lesion a doctor is asking about. Our Solution: We built a multimodal ...