Abstract:

Robotic imitation learning typically requires models that capture multimodal action distributions while operating at real-time control rates and accommodating multiple sensing modalities. Although recent generative approaches such as diffusion models, flow matching, and Implicit Maximum Likelihood Estimation (IMLE) have achieved promising results, they often satisfy only a subset of these requirements. To address this, we introduce MIRROR, a single-pass policy based on a batch-global rejection-sampling variant of IMLE. MIRROR couples a temporal multisensory encoder (integrating RGB, Depth, tactile, audio, and proprioception) with a linear-attention generator using a Performer architecture. We demonstrate the efficacy of MIRROR on a diverse real-world hardware suite, including loco-manipulation using a Unitree GO2 with a 7-DoF arm D1 and tabletop manipulation with a UR5 manipulator. Across challenging physical tasks such as pre-manipulation parking, high-precision insertion, and multi-object pick-and-place, MIRROR outperforms state-of-the-art diffusion policies by 10–25% in success rate while maintaining high-frequency (30–50 Hz) closed-loop control. We further validate our approach on large-scale simulation benchmarks, including CALVIN, MetaWorld, and Robomimic. In CALVIN (10% data split), MIRROR improves success rates by about 25% over diffusion and about 20% over flow matching, while simultaneously reducing trajectory jerk by 20×–50×. These results position MIRROR as a fast, accurate, and multi-sensory imitation policy that retains multimodal action coverage without the latency of iterative sampling