General Intuition has raised $320 million to scale AI trained on millions of hours of gameplay, betting action data can help ...
TL;DR: We study visual spatial reasoning as active visual evidence acquisition. Astra lets a VLM decide when to query an action-conditioned world simulator, inspect the imagined view, and ground the ...
A Stanford-led research team that includes Fei-Fei Li published a benchmark on May 18, 2026, that documents a specific, measurable failure in every frontier multimodal AI model tested: when forced to ...
HERE Technologies, a leading mapping and location technology company, has announced ‘HERE Location Reasoning’ described as a geospatial, advanced grounding solution that will enable AI models, agentic ...
Abstract: Convolutional neural networks (CNNs) have been widely applied to hyperspectral image classification (HSIC). However, traditional convolutions can not effectively extract features for objects ...
Seattle-based artificial intelligence research institute Ai2, the Allen Institute for AI, today announced its next-generation open-source foundation artificial intelligence models, aimed at enabling ...
Abstract: Spatial-temporal relation reasoning is a significant yet challenging problem for video action recognition. Previous works typically apply local operations like 2D or 3D CNNs to conduct space ...
Elorian has raised $55 million in a seed funding round, reaching a $300 million valuation. The company said the raise strengthens its long-term research roadmap. It also signals strong early investor ...
We present a unified aerial VLN framework that operates solely on egocentric monocular RGB observations and natural language instructions. The model formulates navigation as a next-token prediction ...
Today, a pair of developers and a coding tool can replicate enterprise software that once took years to build. This democratization has unlocked a surge of digital efficiency, but it has also birthed ...
Autodesk (ADSK) has invested $200M into Worlds Labs, an artificial intelligence startup that builds spatial reasoning models, according to TechCrunch. World Labs first model, Marble, allows users to ...