Factorized MLLM Embeddings for Composed Image Retrieval Paper • 2611.05193 • Published 6 days ago • 49
DreamX: Video Diffusion Model is a Universal Latent Action Learner Paper • 2611.05377 • Published 6 days ago • 58
L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory Paper • 2610.40614 • Published 11 days ago • 48
ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning Paper • 2610.37666 • Published 13 days ago • 58
Learning the 4D World through Point Trajectory Forecasting Paper • 2610.28594 • Published 20 days ago • 51
GRACE: Generation-aware latent compression for efficient video generation Paper • 2610.10524 • Published Oct 7 • 66
Tetris3D: 3D Scene Generation With Objects That Fit Together Paper • 2610.10539 • Published Oct 7 • 49
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction Paper • 2610.12299 • Published Oct 8 • 55
Speculative Forcing for Efficient Autoregressive Video Generation Paper • 2610.22347 • Published 25 days ago • 79
World Observer: Joint Actor-Observer Generation for Persistent World Modeling Paper • 2610.02162 • Published Oct 1 • 61
DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models Paper • 2603.23499 • Published Mar 24 • 52
Grounding World Simulation Models in a Real-World Metropolis Paper • 2603.15583 • Published Mar 16 • 154
CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Models Paper • 2512.03045 • Published Dec 2, 2025 • 3
Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression Paper • 2512.05081 • Published Dec 4, 2025 • 33