Artemis: Geometry-Grounded Multi-Agent Driving World Models with Shared 3D State and Progressive Memory Update

arXiv:2610.07031 · cs.CV · Submitted 2026-10-04 · Read on arXiv

cs.CV

Submitted: 2026-10-04

Updated: 2026-10-04

Comments: The first three authors contributed equally, and their order was determined by drawing lots. Project Lead: Jiuming Liu. Corresponding Author: Ayush Tewari. Project page: https://liujiuming123.github.io/Artemis/

Project page: https://liujiuming123.github.io/Artemis

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• World Model — 1× in this paper · explained in 7 episodes

Sources

• Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
• Geometric Context Transformer for Streaming 3D Reconstruction
• Context Forcing: Consistent Autoregressive Video Generation with Long Context
• World Models
• RELIC: Interactive Video World Model with Long-Horizon Memory
• MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data
• LIVE: Long-horizon Interactive Video World Modeling
• PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation
• Depth Anything 3: Recovering the Visual Space from Any Views
• Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
• Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends
• UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation
• MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines
• Solaris: Building a Multiplayer Video World Model in Minecraft
• Prisma-World: Camera-Controllable Multi-Agent Video World Model
• Wan: Open and Advanced Large-Scale Video Generative Models
• Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
• MultiWorld: Scalable Multi-Agent Multi-View Video World Models
• Matrix-Game: Interactive World Foundation Model
• SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models