Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains Paper • 2608.09873 • Published 2 days ago • 28
SmartMage: Dynamic Modality Orchestration for 3D Scene Understanding Paper • 2608.05137 • Published 2 days ago • 27
PaDoc: Layout-Grounded Parallel Decoding for Document Parsing Paper • 2608.06146 • Published 6 days ago • 24
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent Paper • 2608.03979 • Published 8 days ago • 50
Scaling Properties of Text Conditioning in Visual Generation Paper • 2607.29679 • Published 12 days ago • 38