← All Posts #Google Research
Deep Dives

How Many Raters Do You Actually Need for a Reliable AI Benchmark?

Google Research digs into the reproducibility crisis in AI evaluation, asking whether it's better to...

0 0
AI News

Vibe Coding XR: Google’s New Trick for Prototyping Spatial Apps in Under a Minute

Google Research combines Gemini Canvas with XR Blocks to let anyone generate interactive, physics-aware WebXR...

0 0
Deep Dives

ConvApparel: Why Your AI User Simulator Might Be Too Polite (And How to Fix It)

Google's new ConvApparel benchmark reveals why LLM-based user simulators are unrealistically patient and knowledgeable, and...

1 0
AI News

Google’s New AI Agents Want to Fix Your Bad Figures and Broken Peer Review

Google Research introduces PaperVizAgent and ScholarPeer, two AI agents designed to help researchers generate publication-ready...

0 0
Deep Dives

Google Research Tries to Figure Out If LLMs Have People Skills

Google Research published a framework for evaluating whether LLMs' behavioral dispositions align with human social...

1 0
Deep Dives

Google’s AI Is Generating Fake Neurons to Speed Up Real Brain Mapping

Google Research's MoGen model generates synthetic neuron shapes to train AI reconstruction systems, cutting errors...

1 0
Deep Dives

Vantage: Google’s New AI Experiment That Scores Your ‘Future-Ready’ Skills

Google Research, in partnership with NYU, launches Vantage—an AI-powered assessment tool that uses generative AI...

1 0
Deep Dives

Simula: A Smarter Way to Generate Synthetic Datasets by Thinking from First Principles

Google Research introduces Simula, a framework that rethinks synthetic data generation as mechanism design. Instead...

1 0