Implicit Maximum Likelihood Estimation (IMLE) achieves multimodal trajectory planning performance comparable to diffusion models while being 100x faster.
March 17, 2026
Original Paper
Implicit Maximum Likelihood Estimation for Real-time Generative Model Predictive Control
arXiv · 2603.13733
The Takeaway
Diffusion-based planners are currently popular but suffer from high latency due to iterative denoising, often making them too slow for real-time control. This work enables the benefits of generative, multimodal planning to be used in high-frequency closed-loop Model Predictive Control (MPC) settings.
From the abstract
Diffusion-based models have recently shown strong performance in trajectory planning, as they are capable of capturing diverse, multimodal distributions of complex behaviors. A key limitation of these models is their slow inference speed, which results from the iterative denoising process. This makes them less suitable for real-time applications such as closed-loop model predictive control (MPC), where plans must be generated quickly and adapted continuously to a changing environment. In this pa