まず座標系、そして一括デコード:System-1世界モデルのための物体中心座標と単一パスデコード
Frame First, Decode Once: Object-Centric Coordinates and Single-Pass Decoding for System-1 World Models
物体の初期姿勢のSE(2)座標系で入出力を表現し単一パスで座標トークンを予測する手法が、System-1世界モデルとしての押し動作予測の精度と速度を大きく改善することを実験的に示した。
分類: cs.CV, cs.AI, cs.LG, cs.RO
原文アブストラクト
Single-pass primitive decoders such as LocateAnything and VFlash predict all quantized coordinate tokens of a geometric primitive in one forward pass, enabling fast, System-1 visual planning. We study what matters when such a decoder serves as a System-1 world model: a fast action-conditioned predictor that ranks candidate pushes by their predicted outcome. On ManiSkill3 PushT-v1 (512 held-out test families, 8,192 rollouts) and on human demonstrations from lerobot/pusht (2,384 test windows), we compare decoders, training losses, rigid-body projections and coordinate frames, using matched checkpoints, hierarchical bootstrap confidence intervals and Holm correction. Two factors of similar size dominate. First, expressing inputs and outputs in the SE(2) frame of the object's initial pose lowers decision regret by 1.9-2.2x for each of five decoders, and the object-frame model trained on 128 families matches the world-frame model trained on 512. Second, single-pass decoding outperforms iterative decoding: in the object frame, single-pass heads reach 0.020-0.021 regret at 1.6-1.8 ms per decision, against 0.046 for 10-step DDIM diffusion and 0.059 for KV-cached autoregression at 10.3 and 12.9 ms. The choice among single-pass heads has no measurable effect on regret, and our registered hypothesis that the frame effect exceeds the decoder spread is not supported. Soft-token expectation with an end-to-end 2D Kabsch projection gives the lowest trajectory error (11.35 px on ManiSkill3, 3.78 px on lerobot/pusht), exact rigid-body consistency, and lower regret than diffusion at every budget from 4 to 50 DDIM steps, at 3-29x lower latency.
