MIT AI learns molecular language for rapid materials development and drug discovery

AI molecular properties concept illustration

MIT-Watson AI Labs’ new AI system dramatically simplifies drug and material discovery by accurately predicting molecular properties with minimal data. The system takes advantage of a molecular grammar learned through reinforcement learning to efficiently generate new molecules. This method has demonstrated remarkable effectiveness even with datasets of less than 100 samples. This AI system needs … Read more

Researchers from ETH Zurich and Microsoft present LightGlue: a deep neural network that learns to match local features in images

Researchers from ETH Zurich and Microsoft present LightGlue: a deep neural network that learns to match local features in images

https://github.com/cvg/LightGlue Matching corresponding points between images is critical for many computer vision applications, such as camera tracking and 3D mapping. The conventional approach is to use scattered points of interest and high-dimensional representations to match them based on their visual appearance. However, accurately describing each problem becomes difficult in scenarios with symmetry, weak textures, or … Read more