Abstract: Existing Video Question Answering (VideoQA) methods face tremendous challenges when dealing with longer videos. On the one hand, long videos contain rich and diverse information at different ...

By combining visual reasoning andcode execution, the model formulates plans to zoom in, inspect, and manipulate images step-by-step. Until now, multimodal models typically processed the world in a ...

Abstract: Understanding camera dynamics is a fundamental pillar of video spatial intelligence. However, existing multimodal models predominantly treat this task as a black-box classification, often ...

At first glance, most people see one thing immediately - and that split-second reaction can reveal more about you than you'd expect. This visual test taps into how your brain naturally processes the ...

Modern multimodal AI models can recognize objects, describe scenes, and answer questions about images and short video clips, but they struggle with long-form and large-scale visual data, where ...

According to Mootion (@Mootion_AI), the company has unveiled an advanced AI video model that delivers smoother and clearer video outputs while offering total user control. The update introduces over ...

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 ...

Medal, a platform for uploading and sharing video game clips, has spun out a new frontier AI research lab that’s using its trove of gaming videos to train and build foundation models and AI agents ...

Spatial reasoning is the ability to perceive, interpret, and act across spatial scales, from millimeter-sized components to distant aerial scenes. All-scale spatial reasoning is fundamental to ...

GeekWire chronicles the Pacific Northwest startup scene. Sign up for our weekly startup newsletter, and check out the GeekWire funding tracker and VC directory. by Taylor Soper on Oct 6, 2025 at 12:55 ...