MoReGen:面向基于代码的文本到视频合成的多智能体运动推理引擎
TLDR
提出物理驱动的MoReGen框架,结合多智能体LLM与模拟器生成符合物理规律的视频,并构建MoReSet基准。
评分理由
The paper addresses an important gap by benchmarking physical validity in T2V generation and proposing a code-based framework with explicit physics simulation. However, the contributions are more about controlled generation and evaluation than learned world models, and the abstract does not provide evidence of real-world interaction or RL integration.
Read-first 评分解释
综合优先阅读分 43.1,由主题、引用、图谱、方法、可复现性和近期性等信号加权得到。 原始总分保留为 15。
研究版图角色
前沿论文方法锚点
排序敏感性
稳定性:volatile;排名波动范围:596。