IEEE

GNN-Based Auto-Encoder for Short Linear Block Codes: A DRL Approach

Abstract: This paper presents a novel auto-encoder based end-to-end channel encoding and decoding. It integrates deep reinforcement learning (DRL) and graph neural networks (GNN) in code design by ...
IEEE

A SPAD-Based Optical Encoder

Abstract: This paper reports on a proof-of-concept SPAD-based (Single Photon Avalanche Diode) optical encoder. The work aims at demonstrating the advantages of SPADs over photodiodes, which are ...
GitHub

Learning-based Sketches for Frequency Estimation in Data Streams without Ground Truth

This work addresses the challenge of frequency estimation in unending data streams, which is vital across domains such as networking, social media, and finance. Traditional sketch-based approaches, ...
GitHub

krafton-ai/Can-Gemini-Embeddings-Be-a-Multimodal-Encoder-for-LLMs-

Exploring whether Google's gemini-embedding-2-preview multimodal embedding API can serve as an encoder for a frozen LLM (Qwen3-4B). A small MLP adaptor (17M params) projects 3072-d embeddings into ...