# 训练世界模型中的客体永久性

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-09-23 08:00
- AIHOT 分数：47
- AIHOT 链接：https://aihot.news/items/cmugc3elz0n0srogvw8uk32rl
- 原文链接：https://arxiv.org/abs/2609.28654

## AI 摘要

研究者推出 WROP，一个包含 150 项认知科学启发任务、分属六个认知类别的数据基础设施，每项任务经 Blender 生成器随机化后产出 1 万+ 样本。团队发布 1.5M 样本训练语料和 300 题考试，评测 14 个视频模型，其中 16B 的 PWM-WROP 在盲测成对 Elo 中位列 continuation 模型第一、总榜第三。

## 正文

Object permanence and solidity are hallmarks of human cognitive priors. Recent studies show that video generation models, a paradigmatic class of current world models, have begun to show emerged reasoning abilities, making them ideal candidates for building human-like physical intelligence. Do video models have emerged object permanence in them? If not, could we train them with a core-cognition inspired dataset? We introduce WROP (World Reasoning with Object Permanence), a data infrastructure of 150 hand-designed cognitive science inspired tasks, divided into six cognitive categories.

We build Blender generators that randomize speed, lighting, camera angle, and other nuisance parameters while preserving each task's cognitive structure, yielding 10,000+ samples per task. We release a 1.5M-sample training corpus and a 300-question exam. On this exam we evaluate 14 video models: 3 reference-to-video, 7 edit, and 4 continuation, among which PWM-WROP, our 16B world model. In a blind pairwise Elo study, PWM-WROP ranks first among continuation models and third overall, behind only a statistical tie between two reference-to-video models.

We release the data, exam, model answers, scores, weights, and PWM, our native-PyTorch training stack on AWS Trainium2.