Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning Article Swipe

MAKE IMPACT

Moritz Reuss , Jyothish Pari , Priyanka Agrawal , Rudolf Lioutikov · YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2412.12953

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/.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2412.12953

PDF

https://arxiv.org/pdf/2412.12953

OA Status

green

Cited By

1

Related Works

10

OpenAlex ID

https://openalex.org/W4405562544

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4405562544

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2412.12953

Digital Object Identifier

Title

Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2024

Year of publication

Publication date

2024-12-17

Full publication date if available

Authors

Moritz Reuss, Jyothish Pari, Priyanka Agrawal, Rudolf Lioutikov

List of authors in order

Landing page

https://arxiv.org/abs/2412.12953

Publisher landing page

PDF URL

https://arxiv.org/pdf/2412.12953

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2412.12953

Direct OA link when available

Concepts

Transformer, Computer science, Electrical engineering, Engineering, Voltage

Top concepts (fields/topics) attached by OpenAlex

Cited by

1

Total citation count in OpenAlex

Citations by year (recent)

2025: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload