Diagnosing the Reference Gap: What Visual Scaffolds Can and Cannot Fix in Multimodal Reasoning Paper • 2610.39419 • Published 14 days ago • 19
OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory Paper • 2610.26860 • Published 24 days ago • 103
LEGATO: Large-scale End-to-end Generalizable Approach to Typeset OMR Paper • 2506.19065 • Published Jun 23, 2025 • 2