SIMIT: Self-Improving Vision-Language Models via Imagination at Test-Time
Paper • 2611.00053 • Published • 6
This is an ad hoc group for people from the Technical University of Denmark with interest in Hugging Face. Note that we have no enterprise solution or SSO.
SIMIT: Self-Improving Vision-Language Models via Imagination at Test-Time
WildRelight: A Real-World Benchmark and Physics-Guided Adaptation for Single-Image Relighting