VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding Paper • 2605.22907 • Published 14 days ago • 4
Nemotron-Personas Collection A collection of multilingual, region-specific synthetic persona datasets that support sovereign AI development across many countries and regions. • 7 items • Updated 5 days ago • 46
Sherlock: Self-Correcting Reasoning in Vision-Language Models Paper • 2505.22651 • Published May 28, 2025 • 47