OverSeer:利用輔助視角提升多智能體世界模型一致性
OverSeer: Multi-Agent World Models Beyond What Agents See
OverSeer 透過加入固定的輔助攝影機視角,改善多智能體世界模型的時間及智能體間一致性。這些半靜態視角以 delta-VAE 編碼相對於靜態參考圖像的變化,減少處理所需的 token,並降低生成輔助視角的計算開銷。Minecraft 和 Doom 實驗顯示世界及智能體一致性有所改善;真實多攝影機影像的定性結果顯示,這種方法不侷限於遊戲引擎。
Published on Oct 20
Authors:
,
,
,
,
,
,
,
Abstract
OverSeer improves multi-agent world models by adding fixed auxiliary camera views that stabilize consistency and are compressed via delta-VAE to reduce computation.
Despite the success of video world models, extending them to multiple agents is difficult because it requires generating several agent-specific video streams that are consistent in time and between agents. To address this gap, we introduce OverSeer, a multi-agent world model that augments egocentric agent views with auxiliary camera views. We suggest that, by fixing the auxiliary views in space, they act as a proxy for a world-centric representation: Unlike the agents' views, which can change entirely due to a simple change in agent position, changes in the auxiliary views directly map to localized changes in the world state. We show that these fixed views substantially help the model to maintain consistency. We also show that, due to their redundant and semi-static nature, the auxiliary views can be efficiently compressed with a delta-VAE that encodes only the changes relative to a static reference image, reducing the number of tokens required to process them. Experiments in Minecraft and Doom demonstrate improved world and agent consistency, with qualitative results on real-world multi-camera captures indicating that the approach is not tied to game engines. Our compression analysis further shows that delta-VAE substantially reduces the computational overhead of auxiliary-view generation. We conclude that these fixed views provide a simple and efficient way to improve multi-agent world models.
View arXiv page View PDF Project page Add to collection
Get this paper in your agent:
hf papers read 2610.28554
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/2610.28554 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/2610.28554 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/2610.28554 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