Learning to Grasp Anything by Playing with Random Toys Paper • 2510.12866 • Published Oct 14, 2025 • 5
Reconstruction Alignment Improves Unified Multimodal Models Paper • 2509.07295 • Published Sep 8, 2025 • 40
LaViDa: A Large Diffusion Language Model for Multimodal Understanding Paper • 2505.16839 • Published May 22, 2025 • 13
LaViDa-1.0 Collection LArge VIsion-language Diffusion moDel with mAsking • 11 items • Updated May 26, 2025 • 8