Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning Paper • 2507.16746 • Published 2 days ago • 26
MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning Paper • 2506.05523 • Published Jun 5 • 34
From Pixels to Prose: A Large Dataset of Dense Image Captions Paper • 2406.10328 • Published Jun 14, 2024 • 18