Neural Cover Selection for Image Steganography

Neural Cover Selection for Image Steganography This blog post is written as an overview and summary of our recent work... Continue

Task-Aware Distributed Source Coding under Dynamic Bandwidth

Deep learning based distributed compression for efficient data transmission in multi-sensor networks Reducing communication overload in multi-sensor networks is becoming... Continue

The Fundamental Limits of Prompt Compression

This blog post is written as an overview and summary of our NeurIPS 2024 paper, Fundamental Limits of Prompt Compression:... Continue

Learning Non-Linear Polar codes via Deep Learning

Setup : Channel coding We consider the problem of reliably communicating a binary message over a noisy channel. The effect... Continue

Estimation of Rate-Distortion Function for Computing with Decoder Side Information

In the ever-evolving landscape of data science, the quest for efficient data compression methods remains a critical challenge. Compression not... Continue

Learning context-dependent autoencoders for CSI feedback

A Motivating Question: How do we cluster different datasets into different groups? When developing data-driven machine learning models for a... Continue

Generating High Dimensional Wireless Channels using Diffusion Models

Significant advancements in deep neural networks have led to developments in wireless communication. However, these deep learning-based methods require extensive... Continue

Learning Codes for Interference Channels

Interference Channels A two-user interference channel is a canonical model for multiple one-to-one communications, where two transmitters wish to communicate... Continue