Factorized MLLM Embeddings for Composed Image Retrieval Paper • 2611.05193 • Published 3 days ago • 47
DreamX: Video Diffusion Model is a Universal Latent Action Learner Paper • 2611.05377 • Published 3 days ago • 55
L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory Paper • 2610.40614 • Published 8 days ago • 47
ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning Paper • 2610.37666 • Published 10 days ago • 58
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction Paper • 2610.12299 • Published 29 days ago • 55
GRACE: Generation-aware latent compression for efficient video generation Paper • 2610.10524 • Published about 1 month ago • 66
Tetris3D: 3D Scene Generation With Objects That Fit Together Paper • 2610.10539 • Published about 1 month ago • 48