HumanNet: Scaling Human-centric Video Learning to One Million Hours Paper • 2605.06747 • Published 6 days ago • 46
When to Trust Imagination: Adaptive Action Execution for World Action Models Paper • 2605.06222 • Published 6 days ago • 39
MG-Nav: Dual-Scale Visual Navigation via Sparse Spatial Memory Paper • 2511.22609 • Published Nov 27, 2025 • 50