DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation
Paper • 2608.13489 • Published • 98
My papers
Papers i keep track of daily
-
-
VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End?
Paper • 2608.15265 • Published • 59 -
MOSS-VL Technical Report
Paper • 2608.15045 • Published • 46 -
MegaParts: Scaling Part-Aware 3D Object Generation to 300 Parts via Token-Efficient Autoregressive Modeling
Paper • 2608.14783 • Published • 19 -
ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval
Paper • 2608.15698 • Published • 6 -
Personalized Auto-Research: Towards a True AI Co-Scientist
Paper • 2608.14881 • Published • 5