← Search

Fabian Wenzel

2 accepted papers

2024

Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals

RSS 2024poster

This work introduces the Multimodal Diffusion Transformer (MDT), a novel diffusion policy framework, that excels at learning versatile behavior from multimodal goal specifications with few language annotations. MDT leverages a diffusion based multimodal transformer backbone and two self-supervised a…

2024

Scaling Robot Policy Learning via Zero-Shot Labeling with Foundation Models

CoRL 2024poster

A central challenge towards developing robots that can relate human language to their perception and actions is the scarcity of natural language annotations in diverse robot datasets. Moreover, robot policies that follow natural language instructions are typically trained on either templated languag…

Cited by 7SourceScholar