IEEE

Real-time Multi-modal Social Event Detection: a New Dataset and A Key Instance-Driven, Quality-Aware Graph Neural Network

Abstract: Social event detection (SED) involves identifying and analyzing significant real-world events using data generated on social media platforms. With the rapid growth of platforms like Weibo ...
Tech Xplore

Easier parameter tuning for prediction using echo state networks

Neural networks, a fascinating technology inspired by the human brain, form the basis of artificial intelligence. These ...

Brain imaging reveals how neural networks coordinate multiple streams at once

Working with concurrent electroencephalogram and functional magnetic resonance imaging technology at the Beckman Institute's ...

Learning to identify new objects reshapes parts of the brain, research finds

The wiring and rewiring of the brain never ends. Neural pathways are constantly being reshaped as we interact with the world ...

Meta launches image generation model with coding, search capabilities

Meta Platforms Inc. today debuted an image generation model that can write code and search the web. Muse Image is the second ...
Communications of the ACM

Can We Understand How Large Language Models Reason?

Large language models can write essays, solve math problems, and generate computer code, but it’s not fully understood how ...
GitHub

From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning (DICE-RL)

DICE-RL is a sample-efficient and stable finetuning framework for diffusion- and flow-based Behavior Cloning policies. Download all checkpoints and datasets from Hugging Face with the following ...
IEEE

Hybrid ConvNeXt-Liquid Neural Network for Satellite Image Classification: A Benchmark on EuroSAT Dataset

Abstract: Recognizing land use and land cover (LULC) elements in satellite imagery is an important foundational point for environmental tracking applications, as well as urban development and ...
Crypto Briefing

Titan Network delivers complete video datasets for AI training at scale

As of early June 2026, Titan Network has reached approximately 4 million connected devices globally. About 1 million of those are online at any given time. The network operates through over 3.8 ...
GitHub

Experimental comparison between a baseline multilayer neural network and a support vector machine for handwritten digit classification on the MNIST dataset.

The experiment analyzes the behavior of both models through training curves, performance metrics, cross-validation partitions, and statistical hypothesis testing. Where $\text{Accuracy}{\text{NNC}}$ ...