Self-Distilling Future Video Representations for World Action Models Paper • 2610.30320 • Published 13 days ago • 50
Learning the 4D World through Point Trajectory Forecasting Paper • 2610.28594 • Published 14 days ago • 54
PointWAM: 3D World Action Modeling for Dexterous Robotic Manipulation Paper • 2610.02840 • Published Oct 2 • 63
CANOPY: Adaptive-Granularity Evidence Compression for Multimodal RAG Paper • 2610.00923 • Published Oct 1 • 21