Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks

Open paper
Benchmark Model Rank Results
object-categorization-on-gritUnified-IOXL–Categorization (ablation): 61.7Categorization (test): 60.8
object-localization-on-gritUnified-IOXL–Localization (ablation): 67.0Localization (test): 67.1

Rank counts only results with a code link.