Factorized MLLM Embeddings for Composed Image Retrieval Paper • 2611.05193 • Published 3 days ago • 45
DreamX: Video Diffusion Model is a Universal Latent Action Learner Paper • 2611.05377 • Published 3 days ago • 54
L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory Paper • 2610.40614 • Published 8 days ago • 47
Projected Representation Conditioning for High-fidelity Novel View Synthesis Paper • 2602.12003 • Published Feb 12
L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory Paper • 2610.40614 • Published 8 days ago • 47
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
Learning the 4D World through Point Trajectory Forecasting Paper • 2610.28594 • Published 17 days ago • 51
GRACE: Generation-aware latent compression for efficient video generation Paper • 2610.10524 • Published 30 days ago • 65
Tetris3D: 3D Scene Generation With Objects That Fit Together Paper • 2610.10539 • Published 30 days ago • 48
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction Paper • 2610.12299 • Published 29 days ago • 55
Speculative Forcing for Efficient Autoregressive Video Generation Paper • 2610.22347 • Published 22 days ago • 79
World Observer: Joint Actor-Observer Generation for Persistent World Modeling Paper • 2610.02162 • Published Oct 1 • 61