Nature

Move over, AlphaFold: open-source model predicts shape of 1 billion proteins

The new open-source atlas, generated by an AI tool called ESMFold2, vastly increases the known protein universe.
IEEE

VLDadaptor: Domain Adaptive Object Detection With Vision-Language Model Distillation

Abstract: Domain adaptive object detection (DAOD) aims to develop a detector trained on labeled source domains to identify objects in unlabeled target domains. A primary challenge in DAOD is the ...
IEEE

Uncertainty-Guided Diffusion Model for Camouflaged Object Detection

Abstract: Recently, diffusion models have significantly improved the performance of Camouflaged Object Detection (COD) by adding noise to a mask and iteratively denoising it to match the target ...
Wired

You Can Disable Gemini in Chrome if It’s Freaking You Out

If you use Google's Chrome browser for desktop, there's probably a Gemini Nano AI model running on your computer right now and taking up about 4 GB of space. That's not necessarily a bad thing, but if ...
Firstpost

Your Google Chrome browser may have installed a 4GB AI model without you noticing

For years, web browsers quietly competed over speed, tabs and memory usage. Now, they are fighting a very different battle: artificial intelligence. And in the process, your browser may be taking up ...
Gizmodo

The Tiny AI Model That Lives Inside the Chrome Browser Hallucinates a Whole Lot

As my colleague wrote on Wednesday, it appears that the Chrome browser quietly and in a squirrel-like fashion hides a 4-gigabyte AI model inside users’ systems in a folder called OptGuideOnDeviceModel ...
GitHub

Any6D: Model-free 6D Pose Estimation of Novel Objects

We introduce Any6D, a model-free framework for 6D object pose estimation that requires only a single RGB-D anchor image to estimate both the 6D pose and size of unknown objects in novel scenes. Unlike ...