Google releases new AI video model Veo 3.1 in Flow and API: what it means for enterprises

As expected after days of leaks and rumors online, Google has unveiled Veo 3.1, its latest AI video generation model, ...

When mathematics meets aesthetics: Tessellations as a precise tool for solving complex problems

In a recent study, mathematicians from Freie Universität Berlin have demonstrated that planar tiling, or tessellation, is ...

Atom-scale stencil patterns help nanoparticles take new shapes and learn new tricks

Inspired by an artist's stencils, researchers have developed atomic-level precision patterning on nanoparticle surfaces, ...
AlphaGalileo

When Mathematics Meets Aesthetics

Researchers at Freie Universität Berlin reveal the mathematics behind mesmerizing patterns / New study links the beauty of ...
AlphaGalileo

AlphaFold 3 Ushers in a New Era for Biomedical Research and Drug Discovery

AlphaFold 3 (AF3), the latest AI model from Google DeepMind and Isomorphic Labs, can predict the structures and interactions ...
IEEE

Robust Category-Level 3D Pose Estimation from Diffusion-Enhanced Synthetic Data

Abstract: Obtaining accurate 3D object poses is vital for numerous computer vision applications, such as 3D reconstruction and scene understanding. However, annotating real-world objects is ...
GitHub

GenDP: 3D Semantic Fields for Category-Level Generalizable Diffusion Policy

We use the SAPIEN to build the simulation environments. To create the data of heuristic policy for single episode, use the following command: python gen_single_episode.py [episode_idx] [dataset_dir] ...