The new model offers performance improvements in reasoning, multimodal understanding and more.

OpenAI's new GPT-5.4 mini model offers performance improvements in reasoning, multimodal understanding and more.
IEEE

A Lightweight Spatial–Spectral Deformable CNN for UAV Hyperspectral Image Classification

Abstract: In recent years, uncrewed aerial vehicle (UAV) technology has shown great potential for application in hyperspectral image (HSI) classification tasks due to its advantages of flexible ...
GitHub

Z80-μLM: A Retrocomputing Micro Language Model

Z80-μLM is a 'conversational AI' that generates short character-by-character sequences, with quantization-aware training (QAT) to run on a Z80 processor with 64kb of ram. The root behind this project ...
IEEE

Query-Oriented Dynamic Multimodal Alignment for Few-Shot Hyperspectral Image Classification

Abstract: Deep learning (DL) has advanced hyperspectral image classification (HSIC), but label scarcity remains a significant challenge. Traditional unimodal methods usually produce unstable ...