← Back to Model Beat
Research·Apr 16·all news from April 16, 2026

Nvidia wants to scale robot simulation training with Lyra 2.0

Nvidia researchers have unveiled Lyra 2.0, a system that generates large, coherent 3D environments from a single photograph. The resulting scenes can be explored in real time and used directly in robot simulations. The article Nvidia wants to scale robot simulation training with Lyra 2.0 appeared first on The Decoder .

Covered by 1 source

Related stories

ResearchAutomated Alignment Researchers: Using large language models to scale scalable oversight - AnthropicApr 14 · 2 sourcesResearchMixAtlas: Uncertainty-aware Data Mixture Optimization for Multimodal LLM MidtrainingApr 16 · 2 sourcesResearchTraining and Finetuning Multimodal Embedding & Reranker Models with Sentence TransformersApr 16ResearchLLMs Gaming Verifiers: RLVR can Lead to Reward HackingApr 17