Study Argues World-Model Simulators Must Be Certified Before Their Safety Verdicts Can Be Trusted新研究提出：世界模型仿真器需先经认证，其安全验证结论才可信
- Across robotics, World Models (WMs) are increasingly used to evaluate action policies by simulating the consequences of actions in an imagined world and returning a success or safety verdict.
- The authors argue a verdict is only as trustworthy as the WM that produced it, meaning the WM itself must first be validated, or "certified," before its judgment can be relied upon.
- They flag that today's video-generation WMs are graded on fidelity metrics such as Fréchet Video Distance (FVD), which reward visual realism but do not check whether the simulated world responds correctly to the policy's actions—including actions unseen during training—a gap directly relevant to any autonomous-driving pipeline that leans on WM-based simulation for policy validation.
- 在机器人领域，世界模型（World Models, WM）正被越来越多地用于评估动作策略——通过在想象世界中模拟动作后果，输出成功或安全与否的判定结果。
- 论文作者指出，判定结果的可信度取决于产生它的世界模型本身，因此世界模型必须先经过验证（即“认证”），其判断才能被采信。
- 他们指出，当前的视频生成类世界模型主要以Fréchet Video Distance（FVD）等保真度指标来评判，这类指标只衡量画面逼真度，却未检验模拟世界是否对策略的动作做出了正确响应（尤其是训练中未见过的动作）——这一缺口对任何依赖世界模型仿真来验证策略的自动驾驶测试流程都直接相关。
