Fast-JEPA:潜在世界モデルの成功と遅延のフロンティアを前進させる
Fast-JEPA: Advancing the Success-Latency Frontier for Latent World Models
潜在世界モデルによる計画を高速化する枠組みで、再帰的ロールアウトを避けて候補行動列の結果を直接予測し、成功率を保ちつつ計画時間を短縮した。動的な分布外条件や実行期限を評価する新ベンチマークDynaGoalも提案。
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: Yao Zhang, Bin Yu, Shijie Lian, Haishan Liu, Changti Wu, Yu Wu, Kai Chen
分類: cs.RO, cs.AI
原文アブストラクト
Latent world models predict the outcomes of action sequences, but comparing candidate plans through recursive rollout remains expensive at test time. We introduce Fast-JEPA, a latent world model planning framework that advances the success-latency Pareto frontier of predictive search. Fast-JEPA reorganizes predictive computation to support effective action-sequence search at low planning cost. It constructs a goal-directed plan to guide search and directly predicts the outcomes of complete candidates for efficient comparison, avoiding recursive state rollout during refinement. Across PushT, Reacher, Cube, and TwoRoom, Fast-JEPA achieves 96.50% average success rate with 2.41x faster planning than INTACT. Search-budget sweeps show that its competitive success and low latency extend across candidate counts and refinement depths. We further introduce DynaGoal, a benchmark for evaluating world-model planning under dynamic out-of-distribution conditions, execution deadlines, and controlled response delays. Fast-JEPA achieves average success rates of 73.83% on DynaGoal-Shift and 87.67% on DynaGoal-Deadline, demonstrating the practical value of low-latency predictive planning under changing control conditions and execution-time constraints. Our code is available at https://github.com/Sofilyzia/Fast-JEPA.
