BirdDreams: Joint Perspective and BEV Video Generation for a Plausible, Reactive Driving World Model Paper • 2611.14815 • Published 11 days ago • 57
Factorized MLLM Embeddings for Composed Image Retrieval Paper • 2611.05193 • Published 18 days ago • 49
DreamX: Video Diffusion Model is a Universal Latent Action Learner Paper • 2611.05377 • Published 18 days ago • 58
L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory Paper • 2610.40614 • Published 23 days ago • 48
ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning Paper • 2610.37666 • Published 25 days ago • 59
Speculative Forcing for Efficient Autoregressive Video Generation Paper • 2610.22347 • Published Oct 15 • 77
KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization Paper • 2610.14448 • Published Oct 10 • 36
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction Paper • 2610.12299 • Published Oct 8 • 55
Tetris3D: 3D Scene Generation With Objects That Fit Together Paper • 2610.10539 • Published Oct 7 • 49
GRACE: Generation-aware latent compression for efficient video generation Paper • 2610.10524 • Published Oct 7 • 65
EgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric Videos Paper • 2609.39378 • Published Sep 30 • 40
World Observer: Joint Actor-Observer Generation for Persistent World Modeling Paper • 2610.02162 • Published Oct 1 • 61
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering Paper • 2609.38177 • Published Sep 29 • 43
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents Paper • 2609.39982 • Published Sep 30 • 96