StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
About
Building generalist embodied agents requires integrating perception, language understanding, and action, which are core capabilities addressed by Vision-Language-Action (VLA) approaches based on multimodal foundation models, including recent advances in vision-language models and world models. Despite rapid progress, VLA methods remain fragmented across incompatible architectures, codebases, and evaluation protocols, hindering principled comparison and reproducibility. We present StarVLA, an open-source codebase for VLA research. StarVLA addresses these challenges in three aspects. First, it provides a modular backbone--action-head architecture that supports both VLM backbones (e.g., Qwen-VL) and world-model backbones (e.g., Cosmos) alongside representative action-decoding paradigms, all under a shared abstraction in which backbone and action head can each be swapped independently. Second, it provides reusable training strategies, including cross-embodiment learning and multimodal co-training, that apply consistently across supported paradigms. Third, it integrates major benchmarks, including LIBERO, SimplerEnv, RoboTwin~2.0, RoboCasa-GR1, and BEHAVIOR-1K, through a unified evaluation interface that supports both simulation and real-robot deployment. StarVLA also ships simple, fully reproducible single-benchmark training recipes that, despite minimal data engineering, already match or surpass prior methods on multiple benchmarks with both VLM and world-model backbones. To our best knowledge, StarVLA is one of the most comprehensive open-source VLA frameworks available, and we expect it to lower the barrier for reproducing existing methods and prototyping new ones. StarVLA is being actively maintained and expanded; we will update this report as the project evolves. The code and documentation are available at https://github.com/starVLA/starVLA.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Robotic Manipulation | LIBERO | Spatial Success Rate98.9 | 314 | |
| Robot Manipulation | SimplerEnv Google Robot tasks Variant Aggregation | Average Success Rate70.2 | 67 | |
| Robotic Manipulation | SIMPLER Visual Matching WidowX robot | Put Spoon on Towel Score90.3 | 51 | |
| Robot Manipulation | SimplerEnv Google Robot Visual Matching | Pick Coke Can95.3 | 43 | |
| Robot Manipulation | RoboTwin Clean 2.0 | -- | 24 | |
| Robot Manipulation | RoboTwin Randomized 2.0 | -- | 20 | |
| Robot Manipulation | RoboCasa-GR1 24 tasks | Average Success Rate48.8 | 10 | |
| Robot Manipulation | RoboTwin | Success Rate (Click Bell)71 | 6 |