Google's Gemini Omni is a new multimodal model that reasons across text, images, audio, and video to generate and edit videos ...

A vision-language-action model is an end-to-end neural network that takes sensor inputs—camera images, joint positions, ...

Xiaomi has open-sourced OneVL, a new AI framework that combines VLA, world models, and latent space reasoning for autonomous driving.

Lung cancer diagnosis relies heavily on interpreting complex computed tomography (CT) images, where accuracy can vary ...

Google released Gemma 4 in early April 2026, and the most striking thing about it isn’t the 256K-token context window or the native audio processing. It’s the license. The entire family of open-weight ...

Abstract: In the rapidly advancing field of computer vision, the application of multimodal models—specifically, vision-language frameworks—has shown substantial promise for complex tasks such as video ...

A team of Apple researchers has developed a new framework that enables high-resolution 3D scene rendering with far greater efficiency. Here are the details of the new study. In a new study titled Less ...

Microsoft Corp. today released a hardware-efficient reasoning model, Phi-4-reasoning-vision-15B, that can process multimodal files such as scientific charts. The model is based on two existing ...

Microsoft on Tuesday released Phi-4-reasoning-vision-15B, a compact open-weight multimodal AI model that the company says matches or exceeds the performance of systems many times its size — while ...

In this post, we share the motivations, design choices, experiments, and learnings that informed its development, as well as an evaluation of the model’s performance and guidance on how to use it. Our ...

Robotics has traditionally used modular pipelines. Perception, planning, and control sit in separate systems and connect through hand-tuned interfaces. This approach works for simple, well-defined ...