PhotoGuider: Composition-Aware Cropping and 360^{circ} View Framing with Explainable Photographic Assessments Paper • 2611.02897 • Published 8 days ago • 39
One Figure, Every Canvas: Editable Flowchart Relayout via Agentic Pipeline Paper • 2610.06852 • Published Oct 5 • 16
OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs Paper • 2610.12461 • Published Oct 8 • 47
PROWBench: Do Video Models Render What the Program Specifies? Paper • 2610.02205 • Published Oct 5 • 42
Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction Paper • 2609.04201 • Published Sep 3 • 39
Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models Paper • 2606.12412 • Published Jun 10 • 20