Video World Models · 2026-10-14
Multics: Generative Multi-Player World Model with Hierarchical Communication
Kaiyi Huang, Wangbo Yu, Yukun Huang, Jiwen Yu, Kunhao Liu, Donglin Yang, Wenbo Hu, Ying Shan, Xihui Liu
AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.
TL;DR
Multics is a multi-player video generation model that uses hierarchical communication (player, group, global) to improve cross-player consistency and controllability while limiting interference between unrelated local events. It introduces shared group tokens for intermediate aggregation and uses budget-constrained dynamic grouping based on recent camera trajectories. The authors report state-of-the-art results on 4- and 6-player settings and generalization from 4-player training to 6-, 8-, and 10-player inference without retraining.
Why it matters
Scalability and robustness are central challenges in multi-player world models. The paper’s hierarchical communication design aims to reduce quadratic attention growth versus fully-connected exchange, while avoiding the interference problems of centralized global representations. Dynamic, budget-constrained grouping further limits unnecessary communication, targeting both efficiency and quality.
Method
- Hierarchical communication: group tokens are inserted into self-attention as intermediate group-level representations, connected to global tokens; this topology limits direct mixing between unrelated local events.
- Shared group-token parameters: group-slot token parameters are shared across group slots, enabling the same communication module to support varying numbers of players without new group-specific parameters or retraining.
- Budget-constrained dynamic grouping: the model estimates pairwise player relevance from recent camera trajectories and selects feasible overlapping groups under a communication budget; remaining players communicate only via global tokens.
Limitation
The authors state that maintaining persistent world states across multiple players over long horizons remains challenging, and that Multics inherits limitations of the pre-trained video foundation model, including visual artifacts under large and dynamic human motions.
Abstract (from arXiv)
Multi-player interactive world models aim to simulate shared environments from multiple players' perspectives, but achieving robust generation while scaling to more players remains challenging. Existing approaches that rely on fully-connected communication (e.g., Solaris) incur quadratic attention costs as the number of players grows, while centralized approaches (e.g., $\gamma$-World) suffer from interference between unrelated events in a shared global representation. To address these challenges, we present Multics, a multi-player video generation framework with hierarchical communication that structures information exchange across player, group, and global levels. This hierarchy introduces group tokens into self-attention as intermediate group-level representations that aggregate locally relevant player information. These tokens connect to global tokens for cross-group communication, while the hierarchical topology limits direct mixing between unrelated local events. Group-token parameters are shared across group slots, allowing the same communication module to accommodate varying numbers of players without introducing new group-specific parameters. We further propose budget-constrained dynamic grouping based on recent camera trajectories, which adaptively groups relevant players while limiting unnecessary communication. Experiments demonstrate that Multics achieves state-of-the-art performance in 4- and 6-player settings, with improved cross-player consistency, player-specific action and camera controllability, and interference robustness. Moreover, Multics generalizes from 4-player training to 6-, 8-, and 10-player inference without retraining, while reducing self-attention computation compared with fully-connected communication.
Related papers
- WorldCast: Distributed Multiplayer World Models
- PAWA: Panoramic Action-conditioned World Modeling for Multiple Agents
- LiveAct: Towards Real-Time Multi-Agent World Models with Heterogeneous Action Interfaces
- Oneira: From Open-Ended Generation to Open-World Interaction in Video World Models
- ActionRoPE: action as coordinates for spatially consistent control in planar-camera game world models
Publication record
Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.
First public release: 2026-10-12 · Indexed by Pub-AI: 2026-10-14 UTC
Multics: Generative Multi-Player World Model with Hierarchical Communication
Preprint posted: 2026-10-12 · Original record ↗
- arxiv
- 2610.17201
Explicit source versions (1)
- v1 · 2026-10-12
- Preprint available
Source date: 2026-10-12 · First detected: 2026-10-25 UTC · Historical baseline
Source evidence (1)
- Official evidence ↗ · atom:published (official metadata)
Abstract · arxiv
Multi-player interactive world models aim to simulate shared environments from multiple players' perspectives, but achieving robust generation while scaling to more players remains challenging. Existing approaches that rely on fully-connected communication (e.g., Solaris) incur quadratic attention costs as the number of players grows, while centralized approaches (e.g., $γ$-World) suffer from interference between unrelated events in a shared global representation. To address these challenges, we present Multics, a multi-player video generation framework with hierarchical communication that structures information exchange across player, group, and global levels. This hierarchy introduces group tokens into self-attention as intermediate group-level representations that aggregate locally relevant player information. These tokens connect to global tokens for cross-group communication, while the hierarchical topology limits direct mixing between unrelated local events. Group-token parameters are shared across group slots, allowing the same communication module to accommodate varying numbers of players without introducing new group-specific parameters. We further propose budget-constrained dynamic grouping based on recent camera trajectories, which adaptively groups relevant players while limiting unnecessary communication. Experiments demonstrate that Multics achieves state-of-the-art performance in 4- and 6-player settings, with improved cross-player consistency, player-specific action and camera controllability, and interference robustness. Moreover, Multics generalizes from 4-player training to 6-, 8-, and 10-player inference without retraining, while reducing self-attention computation compared with fully-connected communication.