空間記憶知能：世界モデルに理解駆動型の長期記憶を付与する
Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory
マルチモーダル大規模言語モデルを活用し、長尺動画の世界モデルにおける空間記憶を管理する初のフレームワークSMIを提案。空間クラスタリングや信頼性フィルタリングなど4つの操作で記憶の疎性・生成安定性・空間一貫性を改善した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Ying Yang, Guiyu Zhang, Lianghua Huang, Chang Nie, Chenyang Si, Haofan Wang, Shaoshuai Shi, Li Jiang
分類: cs.CV
原文アブストラクト
Long-video generation and world models have shown strong potential for interactive entertainment and embodied simulation by predicting future observations conditioned on user actions and historical memory. However, as memory sequences grow longer and their structures become increasingly complex, managing long-range spatial context becomes increasingly challenging, calling for a more intelligent and systematic memory-management strategy. Building on the advancing spatial reasoning capabilities of multimodal large language models (MLLMs) and the broader vision of unified models, we propose Spatial Memory Intelligence (SMI), the first framework to systematically employ an understanding model for spatial-memory management in long-video world models. SMI introduces four coordinated atomic operations: spatial clustering, within-cluster sparsification, action-aware retrieval, and reliability-aware filtering. Extensive experiments across multiple baselines, benchmarks, and world-model backbones demonstrate the effectiveness and generalizability of SMI, achieving comprehensive improvements in memory sparsity, generation stability, and spatial consistency.