Artificial IntelligenceFeatured briefing
First-hand information for everyone
Researchers have created a new kind of building block for 3D graphics called Hexels. Hexels are flat, hexagon‑shaped patches that carry a si
Researchers have created MoI‑Bench, a benchmark focused on mobile image generation and editing. It contains 64 tasks and 1,150 examples, bu
Researchers have assembled the largest private‑access Egocentric Tennis Video (ETV) collection yet. 85 rally sequences were recorded with a
Main discovery ARENA (Active Region attENtion Aggregation) is an attention-based neural network that predicts whether an M‑ or X‑class (M+)
Main discovery The authors show that tumour appearances learned from pre‑operative MR images can guide localisation on intra‑operative CT wi
Main discovery FlexPart is a unified image-to-3D part generation framework. It integrates variable-granularity geometric prompts — sparse po
Main discovery: MVLoMa is a sparse star-graph matcher that extends LoMa from image pairs to multiple views. It avoids repeating reference-si
DewHand is a unified model that directly reconstructs metric world‑space hand motion and camera motion from egocentric (first‑person) video.
GuidedSAM‑Plume is an open‑source, expert‑guided framework designed for the interactive segmentation of volcanic plumes and clouds. (fact1)
A new preprint (arXiv:2610.21902v1) paints a careful picture of a surprising weakness in current multimodal large language models (MLLMs): l