Research

AI Explains Brain Responses to Language

Microsoft ResearchJune 25, 2026high confidence

Why it matters

→GCT provides a method to translate complex AI models into understandable scientific theories.
→It enables the testing of these theories through targeted brain activation experiments.
→This approach could revolutionize how we map and understand brain functions.

AI Explains Brain Responses to Language — ©Microsoft Research

Microsoft Research, along with UC Berkeley, UCSF, and Columbia University, has introduced generative causal testing (GCT) to enhance the interpretability of AI models predicting brain responses to language. GCT distills these models into simple explanations of what brain regions respond to, and tests these explanations by generating stories that activate specific brain areas. This method has confirmed known brain selectivities and uncovered new prefrontal micro-regions. The research, published in Nature Neuroscience, suggests a new approach to understanding brain functions, bridging the gap between predictive models and scientific theories.

Read original

More from Microsoft Research

Researchresearch

Talos Automates Genomic Reanalysis for Rare Diseases

Talos is a groundbreaking open-source tool that automates the reanalysis of genomic data for rare disease diagnosis, significantly improving efficiency and accuracy. By leveraging continuously updated resources like PanelApp Australia and ClinVar, Talos identifies new actionable variants with a low false-positive rate, making it sustainable for large-scale use. In a cohort of nearly 5,000 undiagnosed patients, Talos achieved a 5.1% increase in diagnostic yield, demonstrating its potential to transform genomic reanalysis from a manual, labor-intensive process into a scalable, automated program. This advancement allows for more frequent and systematic reanalysis, ensuring that new scientific discoveries can quickly translate into clinical diagnoses.

Microsoft ResearchJun 24, 2026

More in Research

Researchresearch

MIT Study: AI Enhances Human Critical Thinking

An MIT study finds that combining human skills with AI leads to better performance than relying on human skills alone.

Matt WolfeJun 25, 2026

Researchresearch

Hybrid Models Show Strength in Predicting Meaningful Tokens

Hugging Face's recent study reveals that hybrid language models have distinct advantages over traditional transformers in predicting tokens that carry meaning, such as nouns and verbs. The Olmo Hybrid model outperforms transformers in these areas, showcasing its ability to handle complex language structures. However, when it comes to repetitive tokens, transformers maintain an edge due to their efficient attention mechanisms. This research highlights the importance of evaluating models based on specific token types to uncover architectural strengths. These insights are expected to guide the development of more refined hybrid models, potentially enhancing language model capabilities in the future.

Hugging Face BlogJun 25, 2026

Researchagents

MIT and Microsoft Enhance AI Workflow Efficiency

MIT and Microsoft have developed a system called Murakkab that optimizes AI agent workflows, significantly reducing energy use and costs. By allowing developers to describe workflows in plain language, Murakkab automatically selects the best models and tools, dynamically adjusting configurations to meet user priorities like speed or cost. This innovation addresses inefficiencies in agentic workflows, which are crucial for cloud providers. The system's ability to adapt to new models and hardware without manual reconfiguration marks a significant advancement in AI deployment efficiency.

MIT News AIJun 25, 2026