We present VLA Foundry, an open-source framework that unifies LLM, VLM, and VLA training in a single codebase. Most open-source VLA efforts specialize on the action training stage, often stitching together incompatible pretraining pipelines. VLA Foundry instead provides a shared training stack with end-to-end control, from language pretraining to action-expert fine-tuning. VLA Foundry supports both from-scratch training and pretrained backbones from Hugging Face. To demonstrate the utility of our framework, we train and release two types of models: the first trained fully from scratch through our LLM-->VLM-->VLA pipeline and the second built on the pretrained Qwen3-VL backbone. We evaluate closed-loop policy performance of both models on LBM Eval, an open-data, open-source simulator. We also contribute usability improvements to the simulator and the STEP analysis tools for easier public use. In the nominal evaluation setting, our fully-open from-scratch model is on par with our prior closed-source work and substituting in the Qwen3-VL backbone leads to a strong multi-task table top manipulation policy outperforming our baseline by a wide margin. The VLA Foundry codebase is available at https://github.com/TRI-ML/vla_foundry and all multi-task model weights are released on https://huggingface.co/collections/TRI-ML/vla-foundry. Additional qualitative videos are available on the project website https://tri-ml.github.io/vla_foundry.

翻译：我们提出VLA Foundry，一个在单一代码库中统一LLM、VLM与VLA训练的开源框架。当前多数开源VLA工作专注于动作训练阶段，通常拼接互不兼容的预训练流程。而VLA Foundry提供从语言预训练到动作专家微调的端到端控制的共享训练栈。该框架同时支持从头开始训练和从Hugging Face加载预训练主干网络。为展示框架实用性，我们训练并发布两类模型：第一类通过完整的LLM→VLM→VLA流水线从头训练；第二类基于预训练的Qwen3-VL主干网络构建。我们在开放数据、开源的LBM Eval仿真平台上评估了两类模型的闭环策略性能。此外，我们还对仿真器进行了可用性改进，并贡献了STEP分析工具以便公众使用。在标准评估设置下，我们完全开源的从零训练模型性能与先前闭源工作相当，而替换为Qwen3-VL主干网络后，所获强多任务桌面操作策略在性能上大幅超越基线模型。VLA Foundry代码库已开源至https://github.com/TRI-ML/vla_foundry，所有多任务模型权重发布于https://huggingface.co/collections/TRI-ML/vla-foundry。更多定性演示视频可访问项目官网https://tri-ml.github.io/vla_foundry。