deft skills

6 tagged deft, measured the same way as everything else here.

Browse within: application 5workflow 5

NVIDIA-TAO/tao-skill-bank

Skill Claude CodeCodex

Run the disk-backed DEFT AOI improvement loop for NVIDIA Cosmos Reason 3 / Cosmos3 models, using Nano by default and Edge or Super when explicitly requested: evaluate the base model on Proxy and frozen Benchmark splits, mine real image pairs from Proxy gaps, assemble a per-iteration Train JSON from selected Mining…

86 3d ago A 169 tokens original Apache-2.0