On Tuesday, Nvidia (NVDA) launched Jetson Orin Nano 2, a new robotics computer for entry-level edge AI. The company said it ...

Vision-language models have transformed image analysis by learning joint representations of visual and textual data at scale. Building on contrastive pre-training paradigms, these models enable ...

Computer vision continues to be one of the most dynamic and impactful fields in artificial intelligence. Thanks to breakthroughs in deep learning, architecture design and data efficiency, machines are ...

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 ...

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.

Vision language models (VLMs) have made impressive strides over the past year, but can they handle real-world enterprise challenges? All signs point to yes, with one caveat: They still need maturing ...

The field of optical image processing is undergoing a transformation driven by the rapid development of vision-language models (VLMs). A new review article published in iOptics details how these ...

Liquid AI vision model LFM2.5-VL-3B launches as an open-weight 3.1-billion-parameter release that matches ...

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 ...

Just when you thought the pace of change of AI models couldn’t get any faster, it accelerates yet again. In the popular news media, the introduction of DeepSeek in January 2025 created a moment that ...

DeepSeek trained V4 Flash on 32 trillion tokens worth of training data. The company used an algorithm called Muon to speed up ...