New Apple model combines vision understanding and image generation with impressive results

Manzano combines visual understanding and text-to-image generation, while significantly reducing performance or quality trade-offs.
GitHub

Relational Conformal Prediction for Correlated Time Series (ICML 2025)

This repository contains the code to reproduce the experiments presented in the paper "Relational Conformal Prediction for Correlated Time Series". This project uses the Hydra library to handle the ...
IEEE

CGM-Based Blood Glucose Prediction Model With LSTM Encoder–Decoder Architecture

Abstract: Accurate prediction of blood glucose levels is crucial for automated treatment in diabetic patients. This study proposes a blood glucose prediction model based on an improved attention ...
Frontiers

Beyond the amyloid hypothesis: Leveraging human-centered complex in vitro models to decode Alzheimer's disease etiology

The final, formatted version of the article will be published soon. Alzheimer's disease (AD) is a complex neurodegenerative condition and the leading cause of dementia worldwide. Treatments that ...
GitHub

Sequential Graph-Based Decoding of the Surface Code using a Hybrid Graph and Recurrent Neural Network Model

This Git repo contains simplified source code for creating and testing our combined graph neural network and recurrent neural network used for decoding the surface code.
IEEE

Bridging Models and Language: An Encoder-Decoder Approach for Automated Architectural Documentation with LLMs

Abstract: In modern software development, maintaining consistency between architectural documentation and implementation remains a significant challenge. This research explores how large language ...
marktechpost

Google Introduces T5Gemma 2: Encoder Decoder Models with Multimodal Inputs via SigLIP and 128K Context

T5Gemma 2 follows the same adaptation idea introduced in T5Gemma, initialize an encoder-decoder model from a decoder-only checkpoint, then adapt with UL2. In the above figure the research team show ...