Quantum Breakthrough: Unhackable Keys Sent Over 120 km Using Quantum Dots

Quantum dot–based time-bin QKD achieves stable, long-distance secure communication with practical performance.
eLife

Modality-agnostic decoding of vision and language from fMRI

Modality-agnostic decoders leverage modality-invariant representations in human subjects' brain activity to predict stimuli irrespective of their modality (image, text, mental imagery).

Microsoft launches 3 new AI models in direct shot at OpenAI and Google

Microsoft launches three in-house AI models for transcription, voice, and image generation, challenging OpenAI and Google with lower-cost systems.
IEEE

Image Captioning with Gated Fusion Transformer and Dynamic Encoder Adaptation

Abstract: Automated image captioning is a process of enabling artificial intelligence (AI) models to describe visual content in human language. It is primarily used for enhancing accessibility, ...
IEEE

Causal-augmented Source-free Domain Adaptation with Scale-free Transformer for Schizophrenia Classification

Abstract: Brain functional networks (BFNs) derived from multi-site fMRI data have been widely explored using transformer-based models to extract discriminative connectivity features for the diagnosis ...
GitHub

MathSnap AI — Handwritten Mathematical Expression Recognition

The encoder employs a DenseNet-B (bottleneck) architecture with three dense blocks separated by transition layers. Each bottleneck layer consists of a 1x1 convolution (expanding to 4x growth rate) ...