The interface is localized. Skill descriptions and documents are machine-translated by AI into your language; code, commands, paths and technical terms stay in the original, and the author's document governs.
Explore skills
Design & creative · SKILL.md

semantic-visual-reconstruction

semantic-visual-reconstruction

Add explicit visual supervision to VLMs by training models to autoregressively reconstruct semantic image tokens, achieving 2-3% average gains and 10-point improvements on hallucination robustness.

Independent GitHub snapshot · Automated classification · Original documentation governs

Aadu2021 / skillxivNOASSERTION

Skill documentation

GitHub
Loading documentation from the source…
Saved skills