Pytorch code for IEEE TWC paper "Predictive and Adaptive Deep Coding for Wireless Image Transmission in Semantic Communication"

Deep learning-based task-oriented and unified multi-task semantic communications

Demo of robust semantic communication against semantic noise

Source code for "Deep Joint Source-Channel Coding Over Cooperative Relay Networks", 2024 IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN)

This is a pytorch implementation of digital semantic communication.

Semantic-Forward Relaying: A Novel Framework Towards 6G Cooperative Communications

source codes for paper "RIS-Assisted MIMO Semantic Communication System for Speech Transmission"

This is a pytorch implementation of diffusion models-based image transmission systems.

Source code for paper ''Wireless Point Cloud Transmission'' in SPAWC 2024.

Paper Code for TVT: Resource allocation for semantic communication network

Semantic Message Extraction for Text Based Data With Deep Neural Nets

A repository for my Diploma Thesis; "Semantic communications framework with Transformer based models"

This repo implements a MIMO-based method for semantic communications, learning precoder/decoder pairs to compress latent spaces and align semantics across devices. Includes both a linear ADMM-based model and a neural model under power and complexity constraints.

This repository tackles latent space misalignment in multi-agent AI-native semantic communications. It introduces a federated approach where an access point shares a semantic encoder, while user devices use local semantic equalizers to enhance mutual understanding.

Using Federated Learning to train the model in Semantic Communication in pytorch

Code for "Deep Learning Enabled Semantic Communications with Speech Recognition and Synthesis"

Implements semantic equalization for DeepJSCC, addressing mismatched latent spaces between transmitter and receiver models. Evaluates linear, neural, and zero-shot equalizers for aligning heterogeneous semantics. Enables robust, efficient communication in AI-native wireless systems.

This repository implements a dictionary-driven, sheaf-based semantic communication framework for heterogeneous AI agents, learning both the communication topology and sheaf maps for latent-space alignment, supported by a sparse dictionary–based semantic denoising and compression module that builds a shared global semantic space.

State prediction with semantic extraction from power consumption data