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

cs.CVOct 12, 2026

Multics: Generative Multi-Player World Model with Hierarchical Communication

Authors: Kaiyi Huang, Wangbo Yu, Yukun Huang, Jiwen Yu, Kunhao Liu, Donglin Yang, Wenbo Hu, Ying Shan,

Organizations: The University of Hong Kong · ARC Lab, Tencent IEG

Abstract

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.

Figures & tables

Figure 1: Multics is a multi-player video generation model with hierarchical communication that structures information exchange across player, group, and global levels. Multics can generate robust multi-player videos with cross-player consistency, player-specific controllability, and interference robustness, and can be generalized to more players without retraining.

Figure 2: Overview of Multics . Left : The training pipeline of Multics . The video diffusion model is trained to jointly generate multi-player videos $\mathcal{V}=\{V_{i}\}_{i=1}^{N}$ , conditioned on each player $i$ ’s initial image $I_{i}$ , action sequence $A_{i}$ , camera trajectory $C_{i}$ , and text prompt $P_{i}$ . Right : Comparison of different communication methods. (a) Hierarchical communication in our method; (b) Fully-connected communication in Savva et al. (2026) ; (c) Centralized communication in Liu et al. (2026a) ; (d) Group-based extension of centralized communication with direct intra-group player connections. The matrices illustrate attention connectivity at one latent timestep; block-causal temporal masking and spatial-token expansion are omitted for clarity.

Method	Consistency				Action Accuracy	Camera Accuracy			Visual Quality
Method	GeoKPM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	IDM $\uparrow$	RotErr $\downarrow$	TransErr $\downarrow$	CamMC $\downarrow$	FID $\downarrow$	FVD $\downarrow$
Top: Quantitative Comparison
4 Players
Solaris ( Savva et al., 2026 )	48.51%	17.62	0.4952	0.4324	93.87	2.572	13.50	15.00	28.41	171.9
$\gamma$ -World ( Liu et al., 2026a )	49.42%	17.76	0.5009	0.4293	93.98	2.728	13.66	15.26	29.36	200.5
Ours	54.17%	18.10	0.5005	0.4184	94.17	2.434	11.67	13.21	26.39	162.3

Table 1: Quantitative comparison with previous methods . We compare Multics with Solaris ( Savva et al., 2026 ) and

\gamma

-World ( Liu et al., 2026a ) on consistency, action accuracy, camera accuracy, and visual quality. Top : Results with 4 and 6 players. Middle : Generalization to more players without additional training, where

4\rightarrow N

denotes inference with

N

players using models trained with 4 players. Bottom : Results on EgoTeam. Bold numbers indicate the best result within each setting.

Figure 3: Qualitative comparison of Multics and fully-connected and centralized baselines in 4-/6-player settings. We compare Multics with Solaris ( Savva et al., 2026 ) and $\gamma$ -World ( Liu et al., 2026a ) on (a) cross-player consistency: players observing overlapping views of the same scene and one another; (b) player-specific controllability: adherence to aim-down-sights (ADS) and no-firing controls; and (c) interference robustness: independence of unrelated concurrent events and preservation of a player’s scene upon revisiting despite other players’ movements. Top-down maps are provided for visualization only, and are not used as conditioning inputs. Other players are omitted for clarity, and can be found in supplementary videos.

Figure 4: Qualitative comparison of Multics and fully-connected and centralized baselines in generalizing to 6-/8-/10-player scenarios.

Method	Consistency				Action Accuracy	Camera Accuracy			Visual Quality
Method	GeoKPM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	IDM $\uparrow$	RotErr $\downarrow$	TransErr $\downarrow$	CamMC $\downarrow$	FID $\downarrow$	FVD $\downarrow$
Group-based	48.26%	17.50	0.4878	0.4317	94.02	2.780	13.18	14.91	28.76	158.5
Fixed grouping	50.71%	18.16	0.5052	0.4197	94.05	2.496	12.09	13.71	27.78	168.0
Random grouping	46.76%	17.78	0.5036	0.4329	93.50	4.796	14.61	17.90	29.83	208.2
Ours	54.17%	18.10	0.5005	0.4184	94.17	2.434	11.67	13.21	26.39	162.3

Table 2: Ablation on grouping strategies.

Figure 5: Qualitative ablation study on communication mechanisms. The group-based method exhibits inconsistencies when revisiting previously observed scenes (top) and across player views (bottom).

Figure 6: Comparisons of computational efficiency. Multics reduces computation relative to fully-connected communication and achieves efficiency comparable to centralized and group-based methods.

Figure 7: Effect of communication budget on GeoKPM.

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 8: Generalization from 4 to 6 players. Relative performance degradation of models trained with 4 players compared with the same methods trained with 6 players, all evaluated with 6 players. Lower values indicate better preservation of performance; negative values indicate improvement. Bold labels mark the smallest degradation for each metric. Our method achieves the smallest degradation on six of the eight reported metrics.

Method	Consistency				Action Accuracy	Camera Accuracy			Visual Quality
Method	GeoKPM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	IDM $\uparrow$	RotErr $\downarrow$	TransErr $\downarrow$	CamMC $\downarrow$	FID $\downarrow$	FVD $\downarrow$
Copy group 0	45.01%	16.43	0.4563	0.4797	94.08	4.413	12.91	16.01	26.43	199.0
Copy group 1	43.63%	16.41	0.4557	0.4799	94.04	4.606	13.15	16.38	26.39	200.2
Average both	43.96%	16.41	0.4557	0.4802	94.04	4.765	13.32	16.62	26.82	202.5
Ours	54.33%	16.97	0.4659	0.4517	94.31	3.760	11.15	13.74	21.80	133.8

Appendix

Table 3: Ablation on designs of group-token parameters.

Figure 9: Qualitative comparison on EgoTeam. We compare Solaris, $\gamma$ -World, and Multics on multi-robot egocentric video generation.

Interactive World Models

Interactive world models predict and generate how environments change in response to actions, supporting simulation, planning, and control.

See all 117 papers

WorldCast: Distributed Multiplayer World Models
Oct 8, 2026Ziyang Ye, Junchao Huang, Evelyn Zhang +9World Models Interactive World Models
CUHK-Shenzhen · SLAI · Tsinghua SIGS +2
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
May 27, 2026Fangfu Liu, Kai He, Tianchang Shen +7Interactive World Models Video World Models
NVIDIA · Tsinghua University · University of Toronto +1
Solaris: Building a Multiplayer Video World Model in Minecraft
Feb 25, 2026Georgy Savva, Oscar Michel, Daohan Lu +6Video World Models Action-Conditioned Video Generation
New York University

Oct 8, 2026J/K move · Enter open · S save

WorldCast: Distributed Multiplayer World Models

Ziyang Ye, Junchao Huang, Evelyn Zhang, Zhihao Xie+8

CUHK-Shenzhen · SLAI · Tsinghua SIGS+2

World Models Interactive World Models Real-Time Interactive Video Generation Video World Models

Open paper AskPDF arXiv

Multiplayer world models must generate independently controlled views with consistent representations of both players and their shared environment. Most existing approaches coordinate multiple players through joint multi-view generation, whose cost grows with each additional player. We present WorldCast, a distributed multiplayer world model in which each player runs a local client comprising a video generator and a state model. Using recorded player positions and map geometry during training, the state model estimates the player's position from generated video and control inputs. Clients exchange player states and project them into camera-aligned player state fields that guide where and how other players are rendered. Shared scene state enables clients to reuse one another's generated observations to maintain consistent scene appearance across views. Experiments on Counter-Strike 2 demonstrate WorldCast's consistency, real-time performance, and distributed scalability. The camera-aligned player state field improves player rendering rates by over an order of magnitude over joint-generation methods, while shared scene state improves visual consistency over whole rounds. Each client runs in real time and exchanges only player and scene states, enabling scalable multiplayer generation without a centralized computational bottleneck. Image quality remains stable over hour-long rollouts.

Abstract

Interactive World Models

Explore similar work

WorldCast: Distributed Multiplayer World Models

Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

Solaris: Building a Multiplayer Video World Model in Minecraft