Google Research
8 Posts
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...
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...
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...
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...
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...
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...
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...
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...