One transformer for density and score, across distributions
📄 Tech report: arxiv.org/abs/2511.05924 Many problems in machine learning and the sciences come down to the same task: you have
machine learning
Use Lyria 3 to create music tracks in the Gemini app
New audio verification capabilities All tracks generated in the Gemini app are embedded with SynthID, our imperceptible watermark for identifying
Three Workflows for Improving Vision AI Agent Accuracy With Synthetic Data and Fine-Tuning
Editor’s note: This post is part of Into the Omniverse, a series focused on how developers, 3D practitioners, and enterprises
Salmon in the Loop
One of the most fascinating problems that a computer scientist may be lucky enough to encounter is a complex sociotechnical
Building a VideoAgent-Style Multi-Agent System: Intent Parsing, Graph Planning, and Tool Routing for Video Editing Tasks
def tool_shot_planner(instruction, captions): “””Global-aware storyboard sub-queries from instruction + caption bank.””” bank = “; “.join(sorted({c[“caption”] for c in captions})) if
Building AI Agents? Here Are Some Anti-Patterns to Avoid.
In this article, you will learn the architectural and operational anti-patterns that cause AI agent projects to fail, and how
Agentic RAG: Let the Agent Search
application we build is a RAG app. The recipe is simple: chunk, embed, retrieve, then answer. It looks clean on
Featuring Every Eval Ever Results on Hugging Face Model Pages
Every Eval Ever (EEE) and Hugging Face Community Evals are now intercompatible. We enable cross-posting and interpreting evaluation results, while
Measuring Progress Towards AGI: A Cognitive Framework
To understand AI capabilities across these cognitive abilities, we propose a three-stage evaluation protocol that benchmarks system performance in relation
How Jaiveer Singh Is Helping Robots — and Developers — Move Faster
When Jaiveer Singh talks about robots, he doesn’t begin with spectacle. He begins with infrastructure: the boards inside machines, the