VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification Paper • 2604.01569 • Published Apr 2 • 13
HiCI: Hierarchical Construction-Integration for Long-Context Attention Paper • 2603.20843 • Published 27 days ago
Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale Paper • 2604.11331 • Published 23 days ago