往返一致性：双向扩散模型可预测自身滚动误差
原标题：Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors
AI 摘要
该论文提出了一种双向条件潜扩散模型，通过方向标志控制动力系统在时间上的前向或后向演化，并利用往返一致性（即前向i步再后向i步应回到起点）作为无需测量数据的测试时误差信号。实验表明，该信号在可压缩磁流体动力学、湍流辐射混合层和自然人脸视频上能有效预测滚动误差，并在分布外检测和误差削减上优于基线方法。双向训练成本为负，且后向方向可作为快速逆求解器。
正文节选
Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors Abstract Autoregressive models accumulate error over long rollouts, yet at deployment there is no ground truth to measure it against. We train a single conditional latent diffusion model that steps a dynamical system forward or backward in time via a direction flag, and show that this bidirectionality supplies a measurement-free test-time error signal: rolling forward i steps and then backward i steps mus