Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling Paper • 2508.03404 • Published Aug 5, 2025 • 5
Running on Zero Agents Featured 311 Pixal3D 🏆 311 High-fidelity pixel-aligned image-to-3D generation.
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds Paper • 2604.14268 • Published Apr 15 • 125
Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows Paper • 2603.21210 • Published Mar 22 • 1