Vision Language Models

A new study finds that changing font colors and contrast can hijack AI reasoning in Vision Language Models (VLMs), causing them to overlook words, misread meaning, and reach different conclusions with…

Researchers have introduced Embodied3DBench, a benchmark designed to evaluate low-level spatial intelligence in Vision Language Models (VLMs) within embodied 3D environments. The benchmark includes ov…

Researchers replicated the open-ended image evolution platform Picbreeder by replacing human users with frontier Vision-Language Models (VLMs), finding clear qualitative differences between AI-generat…