ATM:它和通用视觉自监督的关系在于:不是新 SSL 训练法,但给 latent world model 的表征/转移质量提供快速诊断
中高相关;详见方法、贡献和实验边界。
ATM: Action-Consistency Transfer Matrix for Diagnosing and Improving Latent World Models arXiv recent-list补漏 原文链接
编号2606.09028优先级P2类别arXiv recent-list补漏会议arXiv recent-list补漏方法不是新 SSL 训练法,但给 latent world model 的表征/转移质量提供快速诊断来源arXiv / OpenReview
先说结论。它和通用视觉自监督的关系在于:不是新 SSL 训练法,但给 latent world model 的表征/转移质量提供快速诊断。 中高相关;详见方法、贡献和实验边界。
Figureure 1 · : Overview of ATMFigure 1: Overview of ATM. Given a frozen latent world model, ATM constructs true and predicted transition features and trains lightweight inverse probes $h _ { T }$ and $h _ { P }$ post-hoc. Cross-domain probe evaluation produces the $2 \times 2$ Action-Consistency Transfer Matrix, which supports tiered diagnostics, screening and ranking, and the AITS training extension. Snowflake icons denote frozen modules, while flame icons denote trainable heads.这张图概括 ATM 的整体方法流程。阅读时先看模块之间传递的训练信号,再看作者如何把目标拆成可优化的子问题。Figureure 2 · : Cross-model calibration on OGBench-CubeFigure 2: Cross-model calibration on OGBench-Cube. A low-capacity spline model maps ATM diagnostics to success rate for visualization. DINO-WM checkpoints lie near the same trend as LeWMstyle candidates. This analysis is only used for calibration visualization.这张可视化用来解释 ATM 学到的中间表征或对齐关系。重点看它是否支持正文里的机制判断。
核心问题
它和通用视觉自监督的关系在于:不是新 SSL 训练法,但给 latent world model 的表征/转移质量提供快速诊断。