LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning Paper • 2509.24786 • Published Sep 29, 2025 • 6 • 2
HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context Paper • 2506.21277 • Published Jun 26, 2025 • 14 • 1