Model Releases
WorldDiT: A Unified Diffusion Architecture for World and Action Modeling
arXiv:2607.23909v1 Announce Type: new Abstract: Many recent robot policies pursue stronger control by using large pretrained vision-language models (VLMs) as the action backbone. We introduce WorldDiT
arXiv:2607.23909v1 Announce Type: new Abstract: 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.
Related
- AIM: Intent-Aware Unified world action Modeling with Spatial Value Maps
- Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models
- In-Context World Modeling for Robotic Control
- XS-VLA: Coupling Coarse-grained Spatial Distillation with Latent Flow Matching for Lightweight Robotic Control
Source: arXiv cs.LG | 2026-07-28