B, an open-weight multimodal vision AI model designed to deliver strong math, science, document and UI reasoning with far less training data and compute than much larger systems.

Explore how vision-language-action models like Helix, GR00T N1, and RT-1 are enabling robots to understand instructions and act autonomously.

In 2018, I was one of the founding engineers at Caper (now acquired by InstaCart). Sitting in our office in midtown NYC, I remember painstakingly drawing bounding boxes on thousands of images for a ...

Meta’s Llama 3.2 has been developed to redefined how large language models (LLMs) interact with visual data. By introducing a groundbreaking architecture that seamlessly integrates image understanding ...

MIT researchers discovered that vision-language models often fail to understand negation, ignoring words like “not” or “without.” This flaw can flip diagnoses or decisions, with models sometimes ...

Crucially, these tests are generated by custom code and don’t rely on pre-existing images or tests that could be found on the public Internet, thereby “minimiz[ing] the chance that VLMs can solve by ...

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 ...

In the race to develop AI that understands complex images like financial forecasts, medical diagrams and nutrition labels, closed-source systems like ChatGPT and Claude are currently setting the pace, ...

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 ...