LG AI Research Open-Sources EXAONEPath: Transforming Histopathology Image Analysis with a 285M Patch-level Pre-Trained Model for Variety of Medical Prediction, Reducing Genetic Testing Time and Costs

…an experimental design that evaluates research idea generation while controlling for confounders and performs the first head-to-head comparison between expert NLP researchers and an LLM ideation agent. By recruiting over 100 NLP researchers to write novel ideas and blind reviews of both LLM and human ideas, we obtain the first statistically significant conclusion on current LLM capabilities for research ideation: we find LLM-generated ideas are judged as more novel (p < 0.05) than human expert ideas while being judged slightly weaker on feasibility.

New AI system designs proteins that successfully bind to target molecules, with potential for advancing drug design, disease understanding and more.

Agens collaborated in a virtual Minecraft world with emergent economy, culture, religion, and government

Researchers used large language models (LLMs) to expand the sequence diversity of CRISPR-Cas proteins and generate novel, functional genome editors with improved properties compared to natural systems. They publicly released OpenCRISPR-1, the first AI-designed editor for precise genome editing. This novel AI-based approach for designing CRISPR gene editors could potentially expand the capabilities and applications of genome-editing technologies.

…the technology marks another exciting step toward AI and robotics capable of supporting daily life, especially for those users with decreased mobility or motor skills.

Researchers at institutions like the Mayo Clinic and UCLA have successfully developed AI systems that can aid in diagnosing prostate cancer and determining the extent of tumor spread. These advancements have the potential to enhance treatment planning and minimize damage to healthy tissues.

AI-based tool named RENAISSANCE…combines various types of cellular data to accurately depict metabolic states, making it easier to understand how cells function.

100M tokens equals ~10 million lines of code or ~750 novels.

There are force sensors in play that help the cleaning bot to judge how fragile a window pane is, and apply the appropriate pressure for an efficient wash. The company reports that the window cleaning bot employs LiDAR sensors for localization and positioning, while artificial intelligence algorithms ensure stability even in gusty conditions.