Multics: Generative Multi-Player World Model with Hierarchical Communication
cs.CV
Submitted: 2026-10-12
Updated: 2026-10-12
Comments: Project page: https://karine-huang.github.io/Multics/
Code: https://github.com/julien-blanchon/opencs2-dataset
Project page: https://karine-huang.github.io/Multics
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- MASS: Multiplayer World Models with Authoritative Shared State
- Muse: Text-To-Image Generation via Masked Generative Transformers
- Embodied AI Agents: Modeling the World
- DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
- CameraCtrl: Enabling Camera Control for Text-to-Video Generation
- GAIA-1: A Generative World Model for Autonomous Driving
- WanToFight: Real-Time Generative Game Engine for Multi-Player Combat Interaction
- Programmable World Model
- VideoPoet: A Large Language Model for Zero-Shot Video Generation
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- Causal World Modeling for Robot Control
- Dreamitate: Real-World Visuomotor Policy Learning via Video Generation
- Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
- OpenLongTail: Generative Scaling of Long-Tail Driving Data
- Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers
- Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models
- MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines
- Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models
- Solaris: Building a Multiplayer Video World Model in Minecraft
- Prisma-World: Camera-Controllable Multi-Agent Video World Model
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