---
title: "StarVLA"
description: "StarVLA: vla and wam; Verified; 2 variants."
modelId: "starvla"
pageSource: generated
---

StarVLA is a Lego-like modular VLA framework; this catalog entry is GPU-validated: the official QwenOFT predict_action ran on an 80GB CUDA GPU with the local Qwen3-VL-OFT-LIBERO-4in1 checkpoint and Qwen3-VL-4B base VLM. A WM4A world-action checkpoint (Wan2.2-based) is also staged with tensor/import probes but is not promoted by the policy run.

<ModelPaperFigures modelId="starvla" locale="en" />

The recorded paper is [arXiv 2604.05014](https://arxiv.org/abs/2604.05014).

Project page: [starvla.github.io/contributors](https://starvla.github.io/contributors). Code: [starVLA/starVLA](https://github.com/starVLA/starVLA).

<ModelCommandBuilder modelId="starvla" locale="en" />

## What it is for

Pick `starvla-qwen3-vl-oft-libero-4in1` when you want the catalog VLA policy: instruction and observation in, an action trace out. Use it to roll the recorded policy, not to train a new one.

The validated path is QwenOFT: a Qwen3-VL-4B backbone with OFT-style parallel action decoding, fine-tuned on four LIBERO suites in one checkpoint (4in1). The WM4A variant couples the policy with a Wan2.2 world model and remains probe-level.

Catalog tasks include vla, wam, vla policy rollout, and wam world action modeling. Catalog aliases include `Qwen3-VL-OFT-LIBERO-4in1` and `WM4A-Wan2d2-OFT-LIBERO-4in1`. Also recorded: `starvla-wm4a-wan2d2-oft-libero-4in1`.

Recorded evaluation entry points include [LIBERO](/docs/evaluation/benchmark-hub/libero) (The 4in1 checkpoint covers four LIBERO suites).

## Runtime contract

Optional `prompt`, `input_path`, `interactions`, `fps`, and `checkpoint_dir`; artifacts `action_trace` and `starvla_action_trace.json`.

CLI task profiles: `interactive-video`. WorldFoundry binds `StarVLAPipeline`.

Start on `starvla-qwen3-vl-oft-libero-4in1`. The family registers 2 catalog variants (cards above): `starvla-qwen3-vl-oft-libero-4in1` (`vla.policy_rollout`) — Runner parity pending; `starvla-wm4a-wan2d2-oft-libero-4in1` (`wam.world_action_modeling`) — Runner parity pending. Family status: **Verified**.

Use the QwenOFT 4in1 checkpoint for LIBERO evaluation; treat WM4A as staged-but-unvalidated. Stage the Qwen3-VL-4B-Instruct base alongside the policy checkpoint.

WorldFoundry runtime executed official StarVLA QwenOFT predict_action with local Qwen3-VL-OFT-LIBERO-4in1 checkpoint and Qwen3-VL-4B base VLM on an 80GB CUDA GPU.

## Running in WorldFoundry

The catalog launch is `worldfoundry-eval run starvla-qwen3-vl-oft-libero-4in1 --pipeline.task-profile interactive-video`. The command builder above switches `--pipeline.task-profile` among recorded tasks and still emits `worldfoundry-eval run`.

It runs in the unified environment `worldfoundry-unified-cu128` (Python 3.11, CUDA 12.8).

Recorded weight repositories include `StarVLA/Qwen3-VL-OFT-LIBERO-4in1`, `StarVLA/WM4A-Wan2d2-OFT-LIBERO-4in1`, and `Qwen/Qwen3-VL-4B-Instruct` among others. Prepare the environment and check local assets with `bash scripts/inference/prepare_model_infer.sh starvla-qwen3-vl-oft-libero-4in1`. Add `--download` to fetch missing public checkpoints.

Recorded licenses include mit; status: **Verified**.

<ModelRelatedRecipes modelId="starvla" locale="en" />