Thursday, July 16, 2026

1. Mermaid to Unicode Box Art: Introducing grok-mermaid
   T2Simon Willison 博客（Atom）

   Simon Willison introduces grok-mermaid, an open-source tool that converts Mermaid diagrams into Unicode box art. It uses grok to parse Mermaid syntax and generates plain-text Unicode box art suitable for terminals, code comments, and other text-only environments. The tool is lightweight and efficient, requiring no graphical rendering. Key technical aspects include Mermaid parsing, Unicode box generation, and integration with other tools.

2. Multimodal Empirical Bayes Variational Autoencoders for Joint Longitudinal and Time-to-Event Modeling
   T2arXiv AI/CL/LG（论文）

   This paper proposes a multimodal empirical Bayes variational autoencoder (EB-VAE) framework for joint modeling of longitudinal tumor measurements, dropout times, and genetic covariates. The framework uses latent individual effects regularized by a covariate-conditioned prior and combines neural dynamics with a semi-mechanistic decoder to jointly predict tumor growth trajectories and dropout risk. Experiments on melanoma and breast cancer show improved individual-level predictions and identification of biologically plausible genetic indicators such as BRAF and NRAS.

—

1. Microsoft Patches Record 570 Security Vulnerabilities, Citing AI
   T2TechCrunch：AI（RSS）

   Microsoft's July Patch Tuesday fixed a record 570 security vulnerabilities across its product line. The company attributed the surge to its use of AI, which accelerated vulnerability discovery and remediation through AI-powered code analysis and threat detection tools. The patch count increased over 40% from the previous month, setting a new company record.

1. Improving Wind and Solar Power Prediction with Efficient Wrapper-based Feature Selection: An Empirical Study
   T2arXiv AI/CL/LG（论文）

   This paper addresses the lack of systematic feature selection methods in renewable energy prediction by proposing Cluster-based Sequential Feature Selection (CSFS), a novel model-agnostic wrapper method that uses clustering for efficient and reliable feature selection. Evaluated on wind turbine power curve modeling and photovoltaic power prediction, CSFS achieves predictive performance comparable to standard sequential feature selection (SFS) while reducing computational cost by an average of 21%. The paper provides open-source implementation and compares CSFS with filter-based, wrapper-based, and embedded methods, showing wrapper methods generally outperform others.

—