潜在粒子世界モデル：自己教師ありのオブジェクト中心確率動的モデリング
Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling
ビデオデータから教師なしでキーポイントやオブジェクトマスクを発見し、確率的な粒子動力学を学習する世界モデルを提案。実世界のマルチオブジェクトデータセットで最先端の性能を達成し、意思決定タスクにも応用可能。
著者: Tal Daniel, Carl Qi, Dan Haramati, Amir Zadeh, Chuan Li, Aviv Tamar, Deepak Pathak, David Held
分類: cs.LG
原文アブストラクト
We introduce Latent Particle World Model (LPWM), a self-supervised object-centric world model scaled to real-world multi-object datasets and applicable in decision-making. LPWM autonomously discovers keypoints, bounding boxes, and object masks directly from video data, enabling it to learn rich scene decompositions without supervision. Our architecture is trained end-to-end purely from videos and supports flexible conditioning on actions, language, and image goals. LPWM models stochastic particle dynamics via a novel latent action module and achieves state-of-the-art results on diverse real-world and synthetic datasets. Beyond stochastic video modeling, LPWM is readily applicable to decision-making, including goal-conditioned imitation learning, as we demonstrate in the paper. Code, data, pre-trained models and video rollouts are available: https://taldatech.github.io/lpwm-web