Family of tunable vision-language models based on Gemma 2 generate long captions for images that describe actions, emotions, and narratives of the scene. Google has introduced a new family of ...

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 ...

Top AI researchers like Fei-Fei Li and Yann LeCun are developing world models, which don't rely solely on language.

Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now The rise in Deep Research features and ...

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 ...

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 ...

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 ...

Since April, Xiaomi has released a series of open-source foundation models covering language, multimodal and voice ...

Llama has evolved beyond a simple language model into a multi-modal AI framework with safety features, code generation, and multi-lingual support. Llama, a family of sort-of open-source large language ...