WorldDiT: A Unified Diffusion Architecture for World and Action Modeling

Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.

Autores: Sen Wang, R. Gnana Praveen, Bidhan Roy, Marcos Villagra

Resumo

Resumo original (em inglês), extraído do paper:

Many recent robot policies pursue stronger control by using large pretrained vision-language models (VLMs) as the action backbone. We introduce WorldDiT, a unified diffusion transformer architecture that couples action generation with visual world modeling and achieves strong performance without a large pretrained VLM action backbone. During training, a single diffusion transformer generates continuous action chunks and predicts normalized RGB patch targets from future camera frames. Across four LIBERO simulation suites, WorldDiT lies on the reported Pareto frontier for total model parameters and mean success among methods reporting all four suites. These results provide a strong sub-billion-parameter baseline for future scaling studies.

Onde ler

• Página do paper no Hugging Face
• arXiv (resumo) · PDF