Optical illusions are great at testing your visual perception and seeing how your brain interprets visual context, subtle ...

Today's artificial intelligence models can't even tie their own shoes.In new research that puts the latest models to test in a 3D environment, Cornell ...

At the 2025 Cool+ Conference, Manycore Tech officially launched LuxReal, its innovative 3D AI content creation product designed to significantly improve the "spatial consistency" of AI-generated ...

Chinese AI startup Zhipu AI aka Z.ai has released its GLM-4.6V series, a new generation of open-source vision-language models (VLMs) optimized for multimodal reasoning, frontend automation, and ...

Apple has introduced two interesting ways to view photos across its platforms, Spatial Photos and Spatial Scenes, and each adds depth in its own way. Here are the differences and what you need to know ...

General Intuition PBC, a startup developing artificial intelligence models that can navigate three-dimensional environments, has raised $133.7 million in funding. TechCrunch reported today that Khosla ...

Spatial reasoning remains a fundamental challenge for Vision-Language Models (VLMs), with current approaches struggling to achieve robust performance despite recent advances. We identify that this ...

I t was early summer, and Eric Li, who had just finished seventh grade, had two camps to attend in the coming weeks. One was a classic camp in the woods of New Hampshire. The other was the Center for ...

From startups to giants in pharma and tools, the use of spatial biology is growing in importance in drug discovery. LatchBio, a four-year-old San Francisco builder of software and data infrastructure ...

SEATTLE--(BUSINESS WIRE)--Ai2 (The Allen Institute for AI) today announced the release of MolmoAct 7B, a breakthrough embodied AI model that brings the intelligence of state of the art AI models into ...

Bottom line: More and more AI companies say their models can reason. Two recent studies say otherwise. When asked to show their logic, most models flub the task – proving they're not reasoning so much ...

TLDR; the LLMs are great at math in N-dimensions (we tested 1, 2, 3, 4, & 5). BUT when it stops being raw math and starts getting physical and visual, they start to ...