LoongForge-Embodied: A Unified Framework for Training Heterogeneous Embodied Models
Training Vision-Language-Action (VLA) models and World-Action Models (WAMs) is computationally expensive, while their heterogeneous architectures and fragmented training stacks make system optimizations difficult to reuse across models. To address these challenges, we present LoongForge-Embodied, a native-PyTorch framework that unifies and accelerates the training of heterogeneous embodied…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.