Heave-Ho: Decentralized Long-Horizon Multi-Humanoid Collaboration Paper • 2611.22275 • Published 1 day ago • 18
TTB: Test-time Baking for Efficient Rendering of Decoder-only View Synthesis Models Paper • 2611.17331 • Published 7 days ago • 27
One Figure, Every Canvas: Editable Flowchart Relayout via Agentic Pipeline Paper • 2610.06852 • Published Oct 5 • 16
InfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation Paper • 2610.26853 • Published about 1 month ago • 28
Manga2Animate: An Agentic Framework for Faithful Manga Animation with Script and Storyboard Planning Paper • 2610.26851 • Published about 1 month ago • 27
A Diagnostic Study of World-Space Human Recovery Under High Camera Dynamics Paper • 2610.19729 • Published Oct 14 • 19
Every Camera Effect, Every Time, All at Once: 4D Gaussian Ray Tracing for Physics-based Camera Effect Data Generation Paper • 2509.10759 • Published Oct 21, 2025
StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions Paper • 2510.02314 • Published Oct 2, 2025 • 60
YoCausal: How Far is Video Generation from World Model? A Causality Perspective Paper • 2605.30346 • Published May 28 • 50
OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs Paper • 2610.12461 • Published Oct 8 • 48
OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs Paper • 2610.12461 • Published Oct 8 • 48
EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling Paper • 2610.02298 • Published Oct 1 • 16
PROWBench: Do Video Models Render What the Program Specifies? Paper • 2610.02205 • Published Oct 5 • 42
AlayaVista: Streaming World Modeling from Panoramic States to Perspective Video Paper • 2609.14462 • Published Sep 13 • 25
Kaininja: Extending Native 3D Generators to the Part Level Paper • 2609.15659 • Published Sep 14 • 19
WorldSculpt: Generating Compositional Worlds from Grounded Videos Paper • 2609.05416 • Published Sep 4 • 24