The Mask Is Not the Object: Volumetric Supervision for 3D Gaussian Segmentation Paper • 2611.21383 • Published 4 days ago
RelationVGGT: Visual Geometry Transformers for 3D Spatial Relation Segmentation Paper • 2610.00970 • Published Oct 5 • 13
LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation Paper • 2610.12442 • Published Oct 8 • 23
Anisotropic Representations Improve Planning in JEPA World Models Paper • 2609.37441 • Published Sep 29 • 25
Recursive Harness Distillation across Agents for Robot Manipulation Paper • 2609.33378 • Published Sep 27 • 40
HuRo: Robotizing Human Videos for Scalable VLA Pretraining Paper • 2609.10706 • Published Sep 18 • 25
Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding Paper • 2608.07663 • Published Aug 7 • 24
Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition Paper • 2601.16211 • Published Jul 2 • 51
Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views Paper • 2606.29513 • Published Jun 28 • 52