Digitizing Lab Know-How for Safe AI-Assisted Experiments
Explore how AI digitizes lab expertise to bridge the experimental last mile, enhancing safety and accuracy in AI-assisted laboratory support.
MolReAct: LLM-Guided Reinforcement Learning for Lead Optimization
Discover MolReAct, a reinforcement learning framework using LLMs and synthesis-constrained actions to optimize drug leads efficiently and validly.
Localizing and Controlling Policy Circuits in Language Models
Explore how policy routing circuits in language models are localized, scaled, and controlled to enhance safety and performance across model sizes.
Why Refusal-Based AI Alignment Evaluation Fails
Explore why refusal-based AI alignment evaluation is flawed and how routing mechanisms impact AI behavior and censorship strategies.
Data Augmentation for Accurate Dysarthric Speech Severity Estimation
Enhance dysarthric speech severity estimation with data augmentation and AI for robust, scalable clinical assessments and improved speech technology.