Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.

MIT News · Artificial Intelligence · news.mit.edu Jul 15, 2026

3 Questions: Neural transparency and the future of AI design

Assistant Professor Pat Pataranutaporn describes a new interface that lets everyday users glimpse inside an AI's neural network before their chatbot ever says a word.

Microsoft Research Blog · microsoft.com Jul 13, 2026

Verifying Rust cryptography in SymCrypt, from standards to code

Cryptographic code supports vital protections in modern computing systems. Learn how a new method helps verify code as developers write it while preserving speed and adaptability as it gets implemented and evolves. The post Verifying Rust cryptography in SymCrypt, from standards to code appeared first on Microsoft Research.

MIT News · Artificial Intelligence · news.mit.edu Jul 6, 2026

graph neural networks

Interpretable graph neural networks for wind turbine fault feature identification with physics-based constraints and self-supervised pretraining

Asymmetric spatio-temporal synergistic graph neural network for traffic flow forecasting

Benchmarking federated spatio-temporal graph neural networks against lightweight models for IoT intrusion detection: An empirical study on Edge-IIoTset

Feature norm-based regularization for robust out-of-distribution detection in graph neural networks

Prediction of macroscopic mechanical behavior of lunar rock from microstructures: A physics-embedded graph neural network approach

Network-wide fine-grained passenger loading prediction via dynamic relational spatiotemporal deep graph neural networks

Room-level conditional graph neural networks for shear wall layout generation in high-rise buildings

X-ray-free guidewire tracking via arterial pressure sensing in a benchtop vascular model based on a hybrid graph neural network

Constraint-based graph optimization for marine protected area networks: A graph neural network-informed approach

Machine learning-accelerated inverse design of energy materials: A critical review of graph neural networks, physics-informed models, and generative AI for batteries, perovskite solar cells, and electrocatalysts

From tech blogs

How artificial neural networks build their own learning machinery

3 Questions: Neural transparency and the future of AI design

Verifying Rust cryptography in SymCrypt, from standards to code

Toward a future that preserves benefits of neurotechnology for all

NeuralGCM harnesses AI to better simulate long-range global precipitation

Neural Super Sampling is here!