Toggle light / dark theme

Scientists in China have developed contact lenses that let wearers see light normally invisible to the human eye. Cooler still, the lenses work better through closed eyelids, and other versions could help correct color blindness.

The human eye can see a relatively limited range of colors – light with wavelengths of between about 400 and 700 nanometers. In typical human-centric fashion, we call that the ‘visible’ part of the spectrum, even though other animals can see beyond it.

In a new study, scientists have helped humans catch a glimpse of light between 800 and 1,600 nanometers in length, a range we normally can’t see known as infrared. The trick is to pop in a pair of contact lenses embedded with nanoparticles that convert the infrared wavelengths into visible ones.

View recent discussion. Abstract: Modern Vision-Language Models (VLMs) can solve a wide range of tasks requiring visual reasoning. In real-world scenarios, desirable properties for VLMs include fast inference and controllable generation (e.g., constraining outputs to adhere to a desired format). However, existing autoregressive (AR) VLMs like LLaVA struggle in these aspects. Discrete diffusion models (DMs) offer a promising alternative, enabling parallel decoding for faster inference and bidirectional context for controllable generation through text-infilling. While effective in language-only settings, DMs’ potential for multimodal tasks is underexplored. We introduce LaViDa, a family of VLMs built on DMs. We build LaViDa by equipping DMs with a vision encoder and jointly fine-tune the combined parts for multimodal instruction following.

National Institutes of Health (NIH) scientists have developed a new surgical technique for implanting multiple tissue grafts in the eye’s retina.

The findings in animals may help advance treatment options for dry age-related macular degeneration (AMD), which is a leading cause of vision loss among older Americans.