LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling Paper • 2511.20785 • Published 14 days ago • 149
PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image Paper • 2511.13648 • Published 22 days ago • 52
From Pixels to Words -- Towards Native Vision-Language Primitives at Scale Paper • 2510.14979 • Published Oct 16 • 65
RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark Paper • 2509.24897 • Published Sep 29 • 46