- Rating
- 3
- Confidence
- 3(+1)
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
MULTICS is a multi-player video world model with hierarchical communication. It organizes communication at the player, group, and global levels. Group tokens collect information from related players and connect to global tokens. Player groups are updated from recent camera trajectories under a fixed communication budget. Shared group-token parameters allow the model to handle different player counts. Experiments on OpenCS2 and EgoTeam compare MULTICS with fully connected, centralized, and group-based communication. The evaluation covers consistency, controllability, visual quality, efficiency, cross-domain transfer, and inference with more players. The experiments are generally complete and the artchitecture has good scaling potential. I therefore give the paper a score of 3: Borderline Accept.
Critical strengths
-
The hierarchical design is reasonable. Local groups support communication between related players, while global tokens connect different groups. The model can therefore exchange both local and global information.
-
Dynamic grouping is useful. Groups are updated using recent camera trajectories. This is more flexible than fixed grouping and keeps the communication cost bounded.
-
The experiments are fairly complete. The paper compares several communication structures and evaluates the main claims from multiple aspects. The baselines also use the same base model and dataset.
Critical weaknesses
-
The current ablations do not fully isolate the main components of MULTICS. They compare complete communication variants and different grouping strategies, but several factors still change together. In particular, the paper does not separately test direct attention between players in the same group or overlapping group membership. It is also unclear whether fixed, random, and dynamic grouping use the same group size, player coverage, overlap pattern, and communication budget. The authors should start from the full model and remove one component at a time, this would show which parts of the hierarchical design actually improve consistency and controllability.
-
The conditioning design needs more explanation. Keyboard actions use cross-attention, mouse controls use a temporal module, and camera trajectories use Q/K adapters. Why are three different mechanisms needed? Mouse motion and camera trajectories both describe viewpoint changes. How does the model avoid redundant or conflicting conditions? Were more unified designs tested?
-
The evaluated scale is still modest. Training uses four or six players, and evaluation stops at ten. This shows some extrapolation, but not the limit of the method. How do quality, group coverage, memory use, communication cost, and latency change with many more players?
Questions for authors
see weaknesses
5 comments
Response to Reviewer mRsN [Part 2/3]
W2: Why are three different mechanisms needed? Mouse motion and camera trajectories both describe viewpoint changes. How does the model avoid redundant or conflicting conditions? Were more unified designs tested?
A2: 1) We follow previous works to adopt different mechanisms: we follow Gamefactory [A] to use cross attention for discrete keyboard actions, and a temporal module for continuous mouse actions. The ablation in work [A] proves the effectiveness of this action conditioning method. For camera poses, we follow work [B] to adopt a similar mechanism, injecting camera into diffusion latent space by adapters.
2) There exist works [C, D] that incorporate keyboard, mouse actions and camera poses into model training similar to ours.
-
In the aspect of redundancy: in our work, the actions and camera poses serve different roles instead of providing redundant conditions: actions serve as controls for independent players, and camera poses are used for providing global reference coordinate system for multiple players.
-
In the aspect of conflicting conditions: both mouse inputs and camera poses are time-aligned signals from the same gameplay rollout and with little conflicts. Besides, camera trajectories can also be estimated by integrating player actions. Thus, the mouse and camera conditions describe the same viewpoint changes rather than independently or in conflict. To prove this, we follow Lingbot-world[E] to use actions to integrate for camera poses, starting from each player’s first-frame pose. We provide quantitative results of action-derived camera trajectories ("Action-camera") as follows, and the results show comparable performance with our default setting.
GeoKPM ↑ PSNR ↑ SSIM ↑ LPIPS ↓ Action ↑ RotErr ↓ TransErr ↓ CamMC ↓ FID ↓ FVD ↓ Action-camera 55.41% 18.08 0.4992 0.4181 94.11% 2.560 11.88 13.51 26.18 157.6 Ours 54.17% 18.10 0.5005 0.4184 94.17% 2.433 11.73 13.27 26.39 162.3
3) As for the unified design for keyboard, mouse, and camera poses conditions, a possible way is to integrates multiple conditions via unified full-attention mechanisms like in work [F], which we leave for future exploration.
Response to Reviewer mRsN [Part 3/3]
W3: Quality, group coverage, memory use, communication cost, and latency change with many more players
A3: 1) We provide the results of group coverage, memory use, communication cost, and latency change with many more players as follows. As OpenCS2 provides up to 10 players, our quantitative evaluation of quality is limited to that range, which is reported in Table 1 (our method shows advantages on quality from 4 to 10 players). To assess system scalability beyond 10 players, we stress-tested the same checkpoint on larger player sets up to 30 players and measured peak GPU memory, communication cost, and DiT latency for fully-connected, centralized and our methods. Local group coverage is applicable only to our method: fully-connected attention directly connects all players, whereas centralized attention enables all players to exchange information through shared hub tokens. Thus neither baseline constructs local groups, so we report this metric as NA for both.
2) The results show our scalability advantages beyond 10 players: at 30 players, our method uses 68.4x less communication than fully-connected method and reduces DiT latency from 10.59 s to 1.49 s (7.1x speedup). Besides, our method also shows 2.36x less communication and with 1.4x speedup in latency than centralized method. Peak GPU memory grows similarly across methods. Group coverage remains around 91% in the larger-player settings.
Values are ordered as fully-connected / centralized / ours:
| Players | Group coverage (%) | Peak GPU memory (GiB) ↓ | Communication cost (M) ↓ | DiT latency (s) ↓ |
|---|---|---|---|---|
| 4 | 97.39/NA/NA | 30.54 / 31.49 / 30.78 | 414.69 / 145.46 / 37.11 | 0.343 / 0.317 / 0.261 |
| 6 | 96.90/NA/NA | 38.49 / 39.39 / 38.76 | 1,036.73 / 213.94 / 62.87 | 0.622 / 0.453 / 0.348 |
| 10 | 90.99/NA/NA | 54.45 / 55.29 / 54.73 | 3,110.18 / 350.92 / 146.59 | 1.429 / 0.719 / 0.534 |
| 14 | 90.48/NA/NA | 70.40 / 71.18 / 70.85 | 6,289.48 / 487.89 / 188.30 | 2.589 / 0.997 / 0.734 |
| 20 | 90.99/NA/NA | 94.14 / 94.82 / 94.54 | 13,131.89 / 693.35 / 293.15 | 5.001 / 1.404 / 1.009 |
| 30 | 90.99/NA/NA | 133.94 / 134.47 / 134.51 | 30,065.11 / 1,035.79 / 439.71 | 10.590 / 2.080 / 1.489 |
References
[A] Yu J, Qin Y, Wang X, et al. GameFactory: Creating New Games with Generative Interactive Videos[C]//2025 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, 2025: 11590-11599.
[B] Bai J, Xia M, Fu X, et al. Recammaster: Camera-controlled generative rendering from a single video[C]//2025 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, 2025: 14834-14844.
[C] Wang Z, Liu Z, Li J, et al. Matrix-game 3.0: Real-time and streaming interactive world model with long-horizon memory[J]. arXiv preprint arXiv:2604.08995, 2026.
[D] Xiong Z, Song Y, Kang H, et al. ActWorld: From Explorable to Interactive World Model via Action-Aware Memory[J]. arXiv preprint arXiv:2606.17730, 2026.
[E] Team R, Gao Z, Wang Q, et al. Advancing open-source world models[J]. arXiv preprint arXiv:2601.20540, 2026.
[F] Ju X, Ye W, Liu Q, et al. Fulldit: Multi-task video generative foundation model with full attention[J]. arXiv preprint arXiv:2503.19907, 2025.
Please don’t hesitate to let us know if there are any additional clarifications or experiments that we can offer!
Response to Reviewer mRsN [Part 1/3]
We sincerely thank the reviewer for your insightful comments and recognitions to our work, especially for acknowledging that:
We have polished the paper, added the experimental results and made clarifications in the revised version (marked in green). Note that the following polishments have been made according to your advice:
Thanks again for your very constructive comments, which have helped us improve the paper quality significantly! Below we would like to provide point-to-point responses to all the raised questions:
A1: 1) We ablate direct intra-group attention and overlapping group membership separately. Removing direct intra-group attention substantially reduces GeoKPM and camera accuracy, while removing overlapping membership produces a smaller decline in GeoKPM. These results demonstrate that our method improves both consistency and controllability by enabling effective hierarchical communication that structures information exchange across player, group, and global levels.
2) We provide details about fixed, random, and dynamic grouping.