4 citations · 6 across the 32 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
Reliable Trajectory Prediction and Uncertainty Quantification with Conditioned Diffusion Models
Marion Neumeier, Sebastian Dorn, Michael Botsch +1
This work introduces the conditioned Vehicle Motion Diffusion (cVMD) model, a novel network architecture for highway trajectory prediction using diffusion models. The proposed mode…
cs.LG2024
On the Asymptotic Mean Square Error Optimality of Diffusion Models
Benedikt Fesl, Benedikt Böck, Florian Strasser +3
Diffusion models (DMs) as generative priors have recently shown great potential for denoising tasks but lack theoretical understanding with respect to their mean square error (MSE)…