Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning
Track: full paper
Keywords: Diffusion Policies, Imitation Learning, Mixture-of-Experts
TL;DR: Mixture-of-Denoising Experts (MoDE), a novel Diffusion Policy that leverages a noise-conditioned routing strategy to achieve more efficient denoising and improved performance compared to prior approaches.
Abstract: Diffusion Policies have become widely used in Imitation Learning, offering several appealing properties, such as generating multimodal and discontinuous behavior.
As models are becoming larger to capture more complex capabilities, their computational demands increase, as shown by recent scaling laws.
Therefore, continuing with the current architectures will present a computational roadblock.
To address this gap, we propose Mixture-of-Denoising Experts (MoDE) as a novel policy for Imitation Learning.
MoDE surpasses current state-of-the-art Transformer-based Diffusion Policies while enabling parameter-efficient scaling through sparse experts and noise-conditioned routing, reducing both active parameters by 40\% and inference costs by 90\% via expert caching.
Our architecture combines this efficient scaling with noise-conditioned self-attention mechanism, enabling more effective denoising across different noise levels.
MoDE achieves state-of-the-art performance on 134 tasks in four established imitation learning benchmarks (CALVIN and LIBERO).
Notably, by pretraining MoDE on diverse robotics data, we achieve 4.01 on CALVIN ABC and 0.95 on LIBERO-90.
It surpasses both CNN-based and Transformer Diffusion Policies by an average of $57\%$ across 4 benchmarks, while using 90\% fewer FLOPs and fewer active parameters compared to default Diffusion Transformer architectures. Furthermore, we conduct comprehensive ablations on MoDE's components, providing insights for designing efficient and scalable Transformer architectures for Diffusion Policies.
Code and demonstrations are available at https://mbreuss.github.io/MoDE_Diffusion_Policy/.
Presenter: ~Jyothish_Pari1
Format: Yes, the presenting author will attend in person if this work is accepted to the workshop.
Funding: No, the presenting author of this submission does *not* fall under ICLR’s funding aims, or has sufficient alternate funding.
Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.
Submission Number: 29
Loading