New study reveals top AI models still struggle with visual reasoning, exposing hidden weaknesses in today’s multimodal ...

With the emergence of huge amounts of heterogeneous multi-modal data, including images, videos, texts/languages, audios, and multi-sensor data, deep learning-based methods have shown promising ...

OpenMMReasoner emphasizes data quality and diversity over quantity, offering a new path for enterprises to build custom, high-performing AI with limited proprietary data.

OpenAI is rolling out a pair of new artificial intelligence models that mimic the process of human reasoning to field more complicated coding questions and visual tasks, the latest in a flurry of ...

The latest round of language models, like GPT-4o and Gemini 1.5 Pro, are touted as “multimodal,” able to understand images and audio as well as text. But a new study makes clear that they don’t really ...

Young children who practice visual working memory and reasoning tasks improve their math skills more than children who focus on spatial rotation exercises, according to a large study. The findings ...

GPT-5.2 raises accuracy and speed, with 256K token context support, so you get clearer answers on long files and chats.