Deepseek VL-2 is a sophisticated vision-language model designed to address complex multimodal tasks with remarkable efficiency and precision. Built on a new mixture of experts (MoE) architecture, this ...

Imagine a world where your devices not only see but truly understand what they’re looking at—whether it’s reading a document, tracking where someone’s gaze lands, or answering questions about a video.

Phi-3-vision, a 4.2 billion parameter model, can answer questions about images or charts. Phi-3-vision, a 4.2 billion parameter model, can answer questions about images or charts. is a reporter who ...

Hugging Face Inc. today open-sourced SmolVLM-256M, a new vision language model with the lowest parameter count in its category. The algorithm’s small footprint allows it to run on devices such as ...

A research team has developed a chest X-ray vision-language foundation model, MaCo, reducing the dependency on annotations while improving both clinical efficiency and diagnostic accuracy. The study ...

Sarvam AI's new Document intelligence model surpasses the actuary of Gemini 3 Pro, GPT 5.2, and other AI models when it comes ...

Foundation models have made great advances in robotics, enabling the creation of vision-language-action (VLA) models that generalize to objects, scenes, and tasks beyond their training data. However, ...

In April, Microsoft first announced its new Phi-3 family of AI small language models (SMLs). They are designed to be run on devices rather than on cloud servers. Today, as part of Build 2024, ...

DeepSeek, the fast-growing Chinese AI company, is shaking up global technology yet again. Just as the rapid rise of the company's frontier AI models triggered a selloff of U.S. artificial intelligence ...

As I highlighted in my last article, two decades after the DARPA Grand Challenge, the autonomous vehicle (AV) industry is still waiting for breakthroughs—particularly in addressing the “long tail ...