SAGE generates simulation-ready 3D scenes and releases a 10k embodied-AI dataset
rsasaki0109 · x · 2026-07-24
SAGE: Scalable Agentic 3D Scene Generation for Embodied AI proposes an agentic framework that can understand a user-specified embodied task and automatically generate simulation-ready environments at scale.
The release includes:
- code for 3D scene generation
- code for action generation
- the agent-generated SAGE-10k dataset
The goal is to make it easier to build large amounts of training data and environments for embodied-AI research and simulation.
More from Embodied
- NVIDIA open-sources FLORA, a robotics data engine ~125x cheaper than GPT-6 Astra — nvidia · 2026-10-27
- Embodied AI startups need a different operational discipline, investor says — ___Mufasaa · 2026-10-27
- π0.5 study: raising demos from 10 to 438 lifts Place Ball in Bowl success from 7% to 83% — stingning · 2026-10-27
- GPT-6 Astra controls dexterous hands zero-shot at just 5.2% success in 500 trials — stingning · 2026-10-27
- HandsOn benchmark: 66 verified tasks and 18,000 human demos for dexterous manipulation — stingning · 2026-10-27
- DexPort: a handheld interface with a real robot hand for dexterous-hand data collection — pabbeel · 2026-10-27