WorldDynCache：拡散ワールドモデルのためのリスク制御型潜在ダイナミクス近似
WorldDynCache: Risk-Controlled Latent Dynamics Approximation for Diffusion World Model
拡散ワールドモデルの推論を高速化するため、潜在状態遷移のリスクを推定し、条件やフェーズに応じた軽量サロゲートで潜在ダイナミクスを近似するフレームワークを提案。既存のキャッシュ手法より高品質で高速。
著者: Leyang Chen, Junyi Wu, Shaoqiu Zhang, Yulun Zhang
分類: cs.LG, cs.CV
原文アブストラクト
Diffusion world models generate high-quality futures, but re- peated transformer evaluations make inference prohibitively slow. Existing caches reuse intermediate features, selectively update tokens, or reuse and extrapolate denoising outputs ac- cording to local drift or short native-space histories. These criteria can miss both approximation-induced latent transition defects that accumulate across skipped steps and phase- or condition-dependent changes in the direction of latent evo- lution. We propose WorldDynCache, a risk-controlled latent dynamics approximation framework with two core compo- nents. First, a lightweight latent-transition risk estimator tracks the accumulated future impact of approximation defects and calibrates its predictions against counterfactual defects ob- served at exact anchors. Second, a condition- and phase- aware lifted latent surrogate approximates latent evolution without extra transformer evaluations. On HunyuanVoyager- 13B and Aether-5B, WorldDynCache achieves 4.92 times and 2.15 times speedups, respectively, while attaining the best gen- eration quality among the compared caching methods across WorldScore, PSNR, SSIM, and LPIPS.