GST-Bench: Can VLMs Develop Global Spatial Awareness from Video? Paper • 2608.05747 • Published 1 day ago • 27
NOLLI: A Difficulty-Calibrated Puzzle Benchmark for Diagnosing the English-Korean Performance Gap Paper • 2608.04397 • Published 3 days ago • 20
MiniWorld: Democratizing the Training of Video World Models from Scratch Paper • 2608.01127 • Published 6 days ago • 15
ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction Paper • 2607.29677 • Published 8 days ago • 22