High-Fidelity Molecular Generation from Mass Spectra
Discover DualLGD, a novel dual-stream line graph diffusion method boosting molecular generation accuracy from mass spectra by 3x over prior models.
Scalable Framework for Interpretable LLM Evaluation
Discover a scalable, interpretable framework using Item Response Theory to accurately evaluate large language models beyond average accuracy.
Cognitive Agent Compilation for Transparent AI Learning
Discover how Cognitive Agent Compilation enhances AI transparency and control in education, improving problem-solving and learner engagement.
Understanding RL-Jailbreaker Attacks on Large Language Models
Explore how RL-jailbreaker attacks exploit vulnerabilities in LLMs and discover strategies to enhance AI safety against adversarial threats.
BGM-IV: AI Bayesian Model for Nonlinear Instrumental Variables
Discover BGM-IV, an AI-powered Bayesian approach that improves nonlinear instrumental variable analysis with high-dimensional data and causal inference.