MIND：世界模型中的記憶一致性與行動控制基準測試

摘要

世界模型旨在理解、記憶並預測動態視覺環境，然而評估其核心能力的統一基準仍屬匱乏。為填補此空白，我們推出MIND——首個開放領域的閉環重訪基準，用於評估世界模型中的記憶一致性與動作控制能力。MIND包含250段1080p解析度、24幀率的高畫質影片，其中100段（第一人稱）+100段（第三人稱）影片共享動作空間，另有25+25段影片涵蓋八種多樣化場景下的不同動作空間。我們設計了高效評估框架，量化兩項核心能力：記憶一致性與動作控制，以捕捉跨視角的時間穩定性與上下文連貫性。此外，我們構建了多種動作空間（包含不同角色移動速度與鏡頭旋轉角度），用於評估共享場景下跨動作空間的泛化能力。為推動後續性能基準測試，我們提出MIND-World——一種新穎的互動式影片到世界基線模型。大量實驗證實了MIND的完備性，同時揭示了當前世界模型的關鍵挑戰，包括維持長期記憶一致性與跨動作空間泛化的難度。項目頁面：https://csu-jpg.github.io/MIND.github.io/

English

World models aim to understand, remember, and predict dynamic visual environments, yet a unified benchmark for evaluating their fundamental abilities remains lacking. To address this gap, we introduce MIND, the first open-domain closed-loop revisited benchmark for evaluating Memory consIstency and action coNtrol in worlD models. MIND contains 250 high-quality videos at 1080p and 24 FPS, including 100 (first-person) + 100 (third-person) video clips under a shared action space and 25 + 25 clips across varied action spaces covering eight diverse scenes. We design an efficient evaluation framework to measure two core abilities: memory consistency and action control, capturing temporal stability and contextual coherence across viewpoints. Furthermore, we design various action spaces, including different character movement speeds and camera rotation angles, to evaluate the action generalization capability across different action spaces under shared scenes. To facilitate future performance benchmarking on MIND, we introduce MIND-World, a novel interactive Video-to-World baseline. Extensive experiments demonstrate the completeness of MIND and reveal key challenges in current world models, including the difficulty of maintaining long-term memory consistency and generalizing across action spaces. Project page: https://csu-jpg.github.io/MIND.github.io/

MIND：世界模型中的記憶一致性與行動控制基準測試

MIND: Benchmarking Memory Consistency and Action Control in World Models

摘要

Support