NVIDIA releases Cosmos3-Nano LIBERO-10 robot policy checkpoint trained on synthetic data
AINVIDIA publishes a Cosmos3-Nano action policy post-trained on LIBERO-10, a bf16 safetensors checkpoint of about 30 GB loadable by cosmos-framework. The policy scores 94.9 ± 0.4% success on standard scenes and 89.7 ± 1.8% on perturbed scenes, which the source reports against a control model at 4.2 points lower on perturbed scenes.
Source details
NVIDIA · new models on Hugging Face · huggingface.coPublished · added here
Original title: nvidia/cosmos3-nano-libero10-sdg-export-S2_s43