Meta says new AI system can convert brain activity into text without surgery

Meta's new AI, Brain2Qwerty v2, decodes brain signals into text without surgery, achieving 61% word accuracy. This ...
IEEE

FastVLM: Efficient Vision Encoding for Vision Language Models

Abstract: Scaling the input image resolution is essential for enhancing the performance of Vision Language Models (VLMs), particularly in text-rich image understanding tasks. However, popular visual ...
UC Berkeley School of Information

Berkeley Data Science Alums Build Gaze-to-Speech Communication Tool

Master of Information and Data Science (MIDS) alums Katya Aukamp, Beta Desai, Nichol Flowers, and Clara Rhoades are the ...

Can scientists learn cells' language? Researchers aim to decode cellular conversations

Multicellular life depends on remarkable acts of cooperation. Every cell in the human body must sense what is happening ...