跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-12AI 評分35

Multics:採用分層通訊的生成式多玩家世界模型

Multics: Generative Multi-Player World Model with Hierarchical Communication

AI 導讀

Multics 提出採用分層通訊的多玩家影片生成框架,透過玩家、羣組及全局層級組織資訊交換。實驗顯示,Multics 在 4 人及 6 人設定達到最先進水平,並可由 4 人訓練泛化至 6、8、10 人推理,無需重新訓練;與全連接通訊相比,自注意力計算量亦有所減少。

正文

Published on Oct 12

·

Submitted by

Nina

on Oct 14

Authors:

,

,

,

,

,

,

,

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.

View arXiv page View PDF Project page GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.17201

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.17201 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.17201 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.17201 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co