WorldCast: Distributed Multiplayer World Models

Ziyang Ye; Junchao Huang; Evelyn Zhang; Zhihao Xie; Ruicheng Zhang; Boyao Han; Litao Ban; Ziye Wang

cs.CVOct 8, 2026

WorldCast: Distributed Multiplayer World Models

Authors: Ziyang Ye, Junchao Huang, Evelyn Zhang, Zhihao Xie, Ruicheng Zhang, Boyao Han, Litao Ban, Ziye Wang, +4 more

Organizations: CUHK-Shenzhen · SLAI · Tsinghua SIGS · Voyager Research, Didi Chuxing · USTC

Abstract

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.

Figures & tables

Figure 1: Three clients, each running on a separate machine, generate independently controlled views using shared world state. Only the initial frames are provided. Columns show successive moments, with controls annotated above each view; the bottom row shows a top-down layout fitted to the generated views. WorldCast supports real-time generation, cross-view consistency, scalability by adding clients, and distributed execution through state exchange.

Figure 2: (a) Coupled designs generate all players’ views in one model. (b) Each WorldCast player runs its own client, and clients exchange only the shared world state.

Figure 3: A client and the shared world state. Left: player states are projected into the camera-aligned player state field, and each generated block is added to the memory bank of the scene state, from which the next block retrieves one memory entry. Right: the causal video DiT of client $i$ , where the player state field enters after the second DiT block, the memory frames join the recent and target frames, and every frame carries Plücker rays; after block $n$ , the state model estimates the player’s position and the depth of each generated frame, which are published for block $n+1$ .

	FVD $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	Rendered $\uparrow$	Unmatched $\downarrow$
Frame concatenation	48.2	15.37	0.493	0.460	0.074	0.771
Solaris	49.0	15.66	0.501	0.449	0.056	0.739
WorldCast	39.7	16.17	0.507	0.418	0.817	0.039

Table 1: Bidirectional multiplayer generation on ten-second windows. All methods use the same backbone, training data, budget, and GT player positions.

Figure 4: Ten seconds of a held-out round, generated from the first frame and GT player positions (GT: recording with controls; Concat: frame concatenation).

	First 30 s			After 30 s
	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$
Trained without scene state	14.93	0.439	0.507	12.96	0.387	0.603
Scene state off at inference	14.37	0.424	0.545	12.93	0.391	0.615
Only its own earlier blocks	14.56	0.425	0.539	13.53	0.399	0.591
Least-covering memory	14.27	0.421	0.550	12.70	0.380	0.628
WorldCast	14.88	0.431	0.521	14.16	0.409	0.556

Table 3: Scene state over whole rounds. We use GT player positions to exclude the impact of imprecise player position in rendering performance.

Figure 5: State model on a recorded frame: (a) frame, (b) predicted depth, (c) predicted and GT trajectories and visibility over the map.

Figure 6: Serving

P

players on H200 GPUs: (a) FPS per player with decoding, (b) traffic received, (c) attention compute, (d) memory per GPU; Gamma-World and Solaris run on one GPU as released ((b): one player per GPU).

	First 30 s		After 30 s
(a) Scene state	Off	On	Off	On
Mat. Pix. (K) $\uparrow$	72.0	92.1	31.1	44.3
Inliers $\uparrow$	46.2	51.5	18.8	27.7
RotErr ( ∘ ) $\downarrow$	31.8	29.0	59.1	55.6
Depth $\uparrow$	0.243	0.247	0.092	0.120

Table 4: (a) Closed-loop deployment over whole rounds, scene state off at inference and on: agreement between clients. (b) VBench ( Huang et al., 2024 ) over one-hour rollouts.

	FVD $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	Rendered $\uparrow$	Unmatched $\downarrow$
WorldCast	45.7	15.54	0.495	0.455	0.763	0.076
Trained without camera alignment	72.2	15.17	0.490	0.479	0.093	0.826
Trained without visibility	45.8	15.67	0.498	0.449	0.667	0.088
Trained without foreground weight	43.9	15.71	0.500	0.446	0.691	0.060
Trained with late injection	47.2	15.52	0.499	0.456	0.549	0.203
Trained with a coarse field	41.9	15.69	0.497	0.445	0.708	0.083

Table 5: Ablations of the player state field (stage 2, ten-second windows, 6,000 training steps each).

Figure 7: Closed-loop deployment: a whole round generated concurrently, each client on its own GPU and starting from its first recorded frame.

Appendix figures & tables24 assets

Supplementary material from the paper’s appendix.

Appendix

Recorded video
	0–10 s $\downarrow$	50–60 s $\downarrow$	Within two body widths at 60 s $\uparrow$	Blocked $\downarrow$
State model, Eq. ( 4 )	0.46	0.49	0.87	0.19
Extrapolation from the controls	1.86	7.63	0.02	2.38
Place head only	0.56	0.56	0.87	0.24
Motion head only	0.39	2.00	0.53	0.05
Generated video, WorldCast

Appendix

Table 6: Position error in body widths (32 u,

0.61

m) of the clients of the whole rounds of Table 3 , all alive at

60

s, on recorded video and on video generated by WorldCast with GT states: per-client medians over each ten-second interval, then medians over clients, the share of clients within two body widths at

60

s, and, as Blocked, the median error of the one-second displacement over the one-second windows in which the controls imply more than one body width of motion and the GT position moves less than a third of it. Bold marks the better of the state model and extrapolation; the last two rows of each part isolate the motion and place heads of the state model. Extrapolation does not read the video; its two rows differ only in the instants at which the error is evaluated.

FPS per player, including decoding $\uparrow$
Players $P$	2	4	8	10	16
WorldCast , one GPU per player	23.4	23.3	22.5	21.7	18.7
Gamma-World, one GPU	13.0	7.7	4.1	3.3	2.2
Solaris, one GPU	14.2	3.4	1.1	0.7	OOM
Memory per GPU, GiB
WorldCast , one GPU per player	27.1	27.0	27.0	27.1	27.1

Appendix

Table 7: Serving

P

players on H200 GPUs. WorldCast runs one client per player, each on its own GPU, with scene state, as deployed with CUDA graphs, which reproduce its output bit for bit. All

P

clients run concurrently and exchange messages and memory entries, through shared memory on one machine for

P\leq 8

and through a shared file system across two machines for

P=10

and

16

. A client’s frame rate counts its own time per block and excludes the time it waits for the other clients at the lockstep of our evaluations, since, without lockstep, a client reads the latest messages (Appendix B ); the table reports the median over clients and blocks. Gamma-World (2.2B parameters,

320\times 480

; its distilled four-step causal student with a KV cache, the fastest configuration it releases) and Solaris (1.8B,

352\times 640

) run as released, with random weights, all players on one GPU, which is their design. FPS per player includes decoding; memory per GPU is the peak of each framework’s allocator, for WorldCast the largest over clients. At

P=16

, a WorldCast client receives 3.5 Mb/s on average: per block, a 12.0 kB message from each other client and, when it retrieves another client’s memory entry, that entry’s 387 kB of latents. Traffic is received per GPU; for Gamma-World and Solaris it is that of splitting the players one per GPU. Attention compute is the attention FLOPs needed to generate one second of video at 16 fps for all players on the GPU, computed analytically from the query–key products,

2d

operations per pair,

d

being the model width; ∗ the configuration runs out of memory. OOM: the configuration exceeds the memory of one H200.

Stage	Initialization	Steps	Batch	Windows
1: bidirectional tuning, five-second windows	Wan2.2-TI2V-5B	34,000	256	8.70M
then ten-second windows	five-second model	6,000	256	1.54M
2: bidirectional training, player state field	stage 1	25,000	64	1.6M
then scene state	stage 2 at 20,000 steps	5,000	64	320k
3: autoregressive training	stage 2	5,000	64	320k
4: four-step distillation	stage 3	600	64	38.4k

Appendix

Table 8: Training runs of the reported models (Batch: global batch in windows); stages 3 and 4 are run once from each stage-2 model, with and without scene state. The ablations of Table 5 retrain the stage-2 model without scene state from stage 1 for 6,000 steps at a batch of 64 (384k windows). WorldCast denotes the stage-2 model without scene state at 25,000 steps in Table 2 , its 6,000-step checkpoint in Table 5 (the 384k column of Table 9 a), and the four-step model with scene state in Tables 3 , 4 , 6 , 7 , 15 , 16 and 17 – 19 .

Figure 8: Training stages, from a pretrained video model to four-step distillation.

(a) Training windows	64k	128k	256k	384k	512k	768k	1.0M	1.6M
Rendered $\uparrow$	0.617	0.667	0.738	0.763	0.759	0.774	0.784	0.817
Unmatched $\downarrow$	0.154	0.102	0.075	0.076	0.060	0.047	0.044	0.039
PSNR $\uparrow$	15.31	15.51	15.70	15.54	15.66	15.86	15.98	16.17
LPIPS $\downarrow$	0.469	0.456	0.448	0.455	0.444	0.436	0.428	0.418
FVD $\downarrow$	53.0	44.3	43.3	45.7	42.1	43.3	42.9	39.7
(b) Training windows		128k	256k		512k	768k		1.6M

Appendix

Table 9: Scaling with training data on the ten-second windows of Table 2 , with the same entity criterion. (a) The player state field. (b) The render rate of WorldCast , frame concatenation and Solaris at the budgets at which all three were trained and scored, each at its own checkpoint. Frame concatenation starts from a 5,000-step run (640k windows) without player states; its budgets count only windows with states.

WorldCast minus
	First 5 s	Last 5 s
WorldCast	0.257	0.207
Frame concatenation	0.232	0.170
Solaris	0.233	0.179
Recorded video	0.317	0.309
Chance, depth from the most distant instant	0.117	0.116

Appendix

Table 10: Agreement between the depths of the two views of a ten-second window at the same instant, for the three models of Table 2 with GT states: share of pixels whose reprojected depths agree within the larger of

24

u and

5\%

, averaged over the windows; chance places a view’s depth from the most distant instant of its window at its current camera. Differences are paired over windows; their

95\%

bootstrap intervals over windows (10,000 draws) all exclude zero.

	$\Delta$ PSNR	$\Delta$ SSIM	$\Delta$ LPIPS	$\Delta$ Rendered	$\Delta$ Unmatched
WorldCast minus frame concatenation	$+0.80$	$+0.015$	$-0.042$	$+0.631$	$-0.571$
WorldCast minus Solaris	$+0.51$	$+0.006$	$-0.032$	$+0.636$	$-0.592$
Predicted minus GT positions	$-0.38$	$-0.007$	$+0.021$	$-0.058$	$+0.032$

Appendix

Table 11: Paired differences on the ten-second windows of Tables 2 and 2 , whose 95% intervals from 10,000 bootstrap resamples of the windows, with the views of a window resampled together, all exclude zero. PSNR, SSIM and LPIPS report mean per-view differences, while Rendered and Unmatched report median per-view differences, which need not equal the difference between the medians of these tables. FVD compares two distributions of clips and therefore has no paired difference.

	$\Delta$ Rendered			$\Delta$ Unmatched
Setting of the criterion	Concat.	Solaris	Pred.	Concat.	Solaris	Pred.
Match within half a body width	$+0.648$	$+0.656$	$-0.095$	$-0.692$	$-0.709$	$+0.101$
Match within two body widths	$+0.553$	$+0.547$	$-0.038$	$-0.364$	$-0.409$	$+0.012$
Detector confidence $0.25$	$+0.585$	$+0.584$	$-0.064$	$-0.603$	$-0.636$	$+0.029$
Detector confidence $0.5$	$+0.556$	$+0.552$	$-0.090$	$-0.616$	$-0.624$	$+0.025$
Boxes of at least $48^{2}$ pixels	$+0.638$	$+0.632$	$-0.053$	$-0.515$	$-0.521$	$+0.062$

Appendix

Table 12: Table 11 under other settings of the entity criterion (Appendix D ), each changed in the generated and the recorded video alike: WorldCast minus frame concatenation (Concat.) and minus Solaris, and predicted minus GT positions (Pred.). Every difference keeps its sign, and its

95\%

bootstrap interval, computed as in Table 11 , excludes zero.

Whole rounds
	Subject	Background	Motion	Flicker	Dynamic	Imaging	Aesthetic
0–10 s	0.732	0.888	0.953	0.926	1.000	70.8	0.480
10–20 s	0.792	0.917	0.965	0.947	1.000	71.1	0.491
20–30 s	0.822	0.929	0.966	0.948	0.969	71.5	0.499
30–40 s	0.824	0.926	0.966	0.948	0.948	71.8	0.497
40–50 s	0.827	0.929	0.964	0.946	0.958	72.1	0.497

Appendix

Table 13: Reference-free VBench scores of the ten-second windows of the whole rounds (GT states, four-step model trained without scene state) and of the one-hour rollouts of WorldCast with scene state, per twenty-minute interval. Dynamic degree is the fraction of clips classified as moving.

Damage	Subject	Background	Motion	Dynamic	Aesthetic	Imaging
Blur, $\sigma=0.5$ px	$-0.1$	$+0.6$	$+0.3$	$0.0$	$-0.1$	$-5.7$
Blur, $\sigma=2$ px	$-1.1$	$+1.3$	$+1.1$	$0.0$	$-15.7$	$-48.1$
JPEG, quality 30	$-0.5$	$-2.1$	$-0.2$	$0.0$	$-7.7$	$-6.3$
JPEG, quality 12	$-1.6$	$-0.7$	$-0.3$	$0.0$	$-20.4$	$-19.6$
Noise, $\sigma=10$	$-0.8$	$-1.4$	$-0.8$	$0.0$	$-8.6$	$-14.9$
Gamma $1.5$	$-0.1$	$-0.1$	$+0.1$	$0.0$	$-1.3$	$-7.4$

Appendix

Table 14: VBench sensitivity: percent change under paired corruptions of random ten-second windows of the whole rounds, generated by the four-step model trained without scene state (Table 13 ).

	Frames	Rendered by both	Disagreement (u) $\downarrow$
0–10 s	955	0.687	27.4
10–20 s	492	0.626	18.7
20–30 s	652	0.644	19.3
30–40 s	831	0.712	17.0
40–50 s	1,033	0.804	19.2
50–60 s	642	0.715	16.7

Appendix

Table 15: Agreement of two clients on the position of the player of the third client of their round, for WorldCast on the whole rounds with GT states. Frames denotes the number of frames in which that player is scored in both views, and Rendered by both the fraction of these frames in which both clients render it. Disagreement reports, over the frames rendered by both, the median closest distance between the two clients’ viewing rays to the persons matched to that player (one body width is 32 u).

Other players in view	1	2	3	4
Frames	44,395	15,274	3,498	631
Scored pairs	31,525	21,980	7,540	1,941
Rendered $\uparrow$	0.809	0.797	0.795	0.821

Appendix

Table 16: WorldCast on the whole rounds by the number of other players in view. Rendered is pooled over the scored pairs of each level of crowding, since one window mixes levels of crowding.

	FVD $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	Rendered $\uparrow$	Unmatched $\downarrow$
Trained without scene state	78.4	13.60	0.403	0.572	0.815	0.053
Scene state off at inference	90.5	13.40	0.402	0.593	0.820	0.049
Only its own earlier blocks	91.1	13.87	0.407	0.574	0.825	0.042
Least-covering memory	98.5	13.21	0.393	0.602	0.804	0.054
WorldCast	89.3	14.40	0.416	0.545	0.841	0.037
GT frames in the memory bank	75.0	14.99	0.433	0.513	0.853	0.030

Appendix

Table 17: Table 3 over whole rounds, against the recorded video. PSNR, SSIM and LPIPS: means over the ten-second windows; FVD: over their clips; Rendered and Unmatched: medians over views (Appendix D ).

First 30 s
WorldCast minus	$\Delta$ PSNR	$\Delta$ SSIM	$\Delta$ LPIPS
Trained without scene state	$-0.05^{\dagger}$	$-0.0078^{\dagger}$	$+0.0138^{\dagger}$
Scene state off at inference	$+0.51$	$+0.0072^{\dagger}$	$-0.0248$
Only its own earlier blocks	$+0.32$	$+0.0059^{\dagger}$	$-0.0189$
Least-covering memory	$+0.61$	$+0.0097$	$-0.0293$
GT frames in the memory bank	$-0.29$	$-0.0113$	$+0.0163$

Appendix

Table 18: WorldCast minus each other row of Table 3 , paired over the same ten-second windows: mean differences; † marks a

95\%

cluster-bootstrap interval over rounds (10,000 draws) that includes zero. Positive

\Delta

PSNR and

\Delta

SSIM and negative

\Delta

LPIPS favor WorldCast . The last row, GT frames in the memory bank , whose memory entries hold GT frames that clients cannot have, is ahead (negative

\Delta

PSNR and

\Delta

SSIM, positive

\Delta

LPIPS).

GT states
	First 30 s	After 30 s
Trained without scene state	0.259	0.135
Scene state off at inference	0.229	0.133
Only its own earlier blocks	0.231	0.147
Least-covering memory	0.225	0.119
WorldCast	0.264	0.206

Appendix

Table 19: Agreement between the depths predicted for two clients’ generated frames at the same instant, on the whole rounds of Table 3 with GT states and, in the lower part, in the closed-loop deployment of Table 4 a with the cameras each client publishes: share of pixels whose reprojected depths agree within the larger of

24

u and

5\%

; chance places a client’s depth from 10 s later at its current camera. Differences are paired over rounds; † marks a

95\%

cluster-bootstrap interval over rounds (10,000 draws) that includes zero. Own next latent frame applies the same measure to each client and its own next latent frame; scene state does not change it, so its gain between clients is not a steadier depth estimate.

Row minus WorldCast	$\Delta$ PSNR	$\Delta$ SSIM	$\Delta$ LPIPS	$\Delta$ Rendered	$\Delta$ Unmatched
Trained without camera alignment	$-0.37$	$-0.005$	$+0.024$	$-0.545$	$+0.560$
Trained without visibility	$+0.13$	$+0.003$	$-0.006$	$-0.047$	$0.000^{\dagger}$
Trained without foreground weight	$+0.17$	$+0.006$	$-0.009$	$-0.043$	$0.000^{\dagger}$
Trained with late injection	$-0.02^{\dagger}$	$+0.004$	$+0.001^{\dagger}$	$-0.148$	$+0.051$
Trained with a coarse field	$+0.15$	$+0.003$	$-0.010$	$-0.034$	$0.000^{\dagger}$
Field off at inference	$-0.20$	$-0.003$	$+0.012$	$-0.690$	$+0.192$

Appendix

Table 20: Each row of Table 5 minus WorldCast , paired over the views both rows score (PSNR, SSIM, LPIPS: mean difference; Rendered, Unmatched: median per-view difference, which need not equal the difference between the medians of Table 5 ); † marks a

95\%

interval from 10,000 bootstrap resamples of the windows, the two views of a window drawn together, that includes zero. Negative

\Delta

PSNR,

\Delta

SSIM and

\Delta

Rendered and positive

\Delta

LPIPS and

\Delta

Unmatched mean that the row is behind WorldCast . FVD compares two distributions of clips and has no paired difference.

Figure 9: Nuke round 13, player 2; rows and overlays as in Fig. 4 .

Figure 10: Nuke round 13 of another match, player 1; rows and overlays as in Fig. 4 .

Figure 11: Nuke round 2, player 7; rows and overlays as in Fig. 4 .

Figure 12: Ancient round 22, player 5; rows and overlays as in Fig. 4 .

Figure 13: Ancient round 18, player 1; rows and overlays as in Fig. 4 .

Panel of Figure 14 — Figure 14: Mirage round 16, one client, whole round with GT states. GT: recording; SceneOff: scene state off at inference; NoScene: trained without scene state. After 30 s, WorldCast keeps the scene of the recording and in the third column returns to the wall of its first frame; SceneOff and NoScene generate other parts of the map.

Panel of Figure 16 — Figure 16: Ancient round 11, one player, ten-second window of Table 2 . GT: recording; Oracle: GT positions; Predicted: positions predicted in closed loop, every client estimating its own position from its generated video, with visibility from the depth head.

Panel of Figure 18 — Figure 18: Mirage round 11, closed-loop deployment of Table 4 a: all five players of one team run clients with predicted states; three are shown. Off/On: scene state off/on; a player’s Off and On rows differ only in scene state. With scene state, the three views stay around the A-site ramp and agree on its landmarks, and Players 2 and 3 draw the teammates ahead of them (supplementary videos).

Explore similar work

MASS: Multiplayer World Models with Authoritative Shared State
Aug 6, 2026Ziqi Cai, Siqi Yang, Yimu Wang +6Multi-View Consistency World Model Learning
1Alaya Lab 2Peking University 3Institute of Science Tokyo
Multiplayer Interactive World Models with Representation Autoencoders
Jul 6, 2026Anthony Hu, Václav Volhejn, Adrien Ramanana Rahary +24Action-Conditioned World Models Latent World Models
1General Intuition · 2Kyutai · ‡École nationale des ponts et chaussées +1
MultiWorldBench: Do Independently Controlled Views Describe One Shared World?
Oct 8, 2026Zhangbo Xu, Ruoxi Zhang, Rui Hu +1Multi-View Consistency World Model Evaluation
Zhiying Guangnian Technology Co., Ltd.

Aug 6, 2026, cs.CVJ/K move · Enter open · S save

MASS: Multiplayer World Models with Authoritative Shared State

Ziqi Cai, Siqi Yang, Yimu Wang, Zixian Gao+5

1Alaya Lab 2Peking University 3Institute of Science Tokyo

Multi-View Consistency World Model Learning State Tracking Video World Models

Open paper AskPDF arXiv

Current video world models struggle in multiplayer environments because they entangle world state with view-dependent visual latents, leading to redundant compute, view inconsistencies, and poor scalability. We propose MASS (Multiplayer world models with Authoritative Shared State) to resolve this limitation. Inspired by multiplayer game architectures, MASS disentangles world dynamics and view rendering. A learned Logic Engine advances a global, authoritative typed state from joint actions without any hand-written transition function, acting as the sole recurrent memory and synchronization reference. From this shared state, a learned Rendering Engine generates independent and consistent views for any requested camera on demand. This explicit disentangling allows MASS to achieve superior state accuracy and lower cross-view inconsistency compared to state-of-the-art multi-view baselines on a matched multiplayer Snake benchmark. It advances predicted worlds with 1,024 concurrent players for 10,000 recurrent steps. Our results show that explicit, authoritative state modeling provides a practical foundation for scalable and consistent multi-agent world simulation.

Abstract

Explore similar work

MASS: Multiplayer World Models with Authoritative Shared State

Multiplayer Interactive World Models with Representation Autoencoders

MultiWorldBench: Do Independently Controlled Views Describe One Shared World?