Learn how ChatGPT Image 2 improves upon previous models with a 250-point ELO score jump, better aspect ratio flexibility, and ...

Anthropic has released Claude Opus 4.7, an updated large language model that it says outperforms its predecessor on software engineering tasks, image analysis, and multi-step autonomous work.

Montgomery, Alabama — Happy Horse 1.0 has ranked first in pure visual quality on the Artificial Analysis Video Arena, a blind human-vote Elo leaderboard that evaluates AI video generation models based ...

A study on visual language models explores how shared semantic frameworks improve image–text understanding across ...

OpenAI launches ChatGPT Images 2.0 with improved instruction accuracy, reasoning capability, multilingual support, flexible ...

OpenAI has unveiled ChatGPT Images 2.0, a new image generation model designed to push beyond standard text-to-image tools and ...

Alibaba Cloud, the cloud services and storage division of the Chinese e-commerce giant, has announced the release of Qwen2-VL, its latest advanced vision-language model designed to enhance visual ...

Alibaba has released QVQ-Max, a new visual reasoning model that it says can see, understand, and think about the world. Alibaba, the Chinese tech giant, has announced a new Qwen AI bot called QVQ-Max, ...

Nano Banana Pro can use Google Search to research topics based on your query, and reason on how to present factual and grounded information. Nano Banana Pro excels in visual design, world knowledge, ...

HBP researchers have trained a large-scale model of the primary visual cortex of the mouse to solve visual tasks in a highly robust way. The model provides the basis for a new generation of neural ...