MLLMs Need 3D-Aware Representation Supervision for Scene Understanding Paper • 2506.01946 • Published Jun 2, 2025 • 3
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation Paper • 2609.11638 • Published 18 days ago • 700
Elastic Token Compression for Pixel-Space Diffusion Transformers Paper • 2608.29281 • Published 30 days ago • 1