# Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

arXiv: https://arxiv.org/abs/2605.30280 · HTML: https://mlsanity.com/paper/2605.30280/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Placed in Human-video and latent-action pretraining, one of 13 directions in Vision-language-action models.
- Builds on 78 of its 90 references that are in the map.
- First posted on arXiv 28 May 2026.

## Placed in

- Vision-language-action models / [Human-video and latent-action pretraining](https://mlsanity.com/vla/human-video-and-latent-action-pretraining/)

## Builds on (most cited first, 30 of 78)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (2025)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023)
- [Evaluating Real-World Robot Manipulation Policies in Simulation](https://mlsanity.com/paper/2405.05941/) (2024)
- [DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model](https://mlsanity.com/paper/2310.01412/) (2023)
- [Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2004.02857/) (2020)
- [Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding](https://mlsanity.com/paper/2010.07954/) (2020)
- [RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots](https://mlsanity.com/paper/2406.02523/) (2024)
- [Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation](https://mlsanity.com/paper/2401.02117/) (2024)
- [Causal World Modeling for Robot Control](https://mlsanity.com/paper/2601.21998/) (2026)
- [X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model](https://mlsanity.com/paper/2510.10274/) (2025)

## Built on by (most cited first, 30 of 44)

- [ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?](https://mlsanity.com/paper/2606.19531/) (2026)
- [ABot-M0.5: Unified Mobility-and-Manipulation World Action Model](https://mlsanity.com/paper/2607.00678/) (2026)
- [From Foundation to Application: Improving VLA Models in Practice](https://mlsanity.com/paper/2607.06403/) (2026)
- [Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack](https://mlsanity.com/paper/2606.14409/) (2026)
- [G0.5: One Autoregressive Stream for Robot Reasoning and Action](https://mlsanity.com/paper/2608.11739/) (2026)
- [TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM](https://mlsanity.com/paper/2607.27205/) (2026)
- [Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving](https://mlsanity.com/paper/2609.00111/) (2026)
- [Hy-Embodied-VLM-1.0: Efficient Physical-World Agents](https://mlsanity.com/paper/2607.12894/) (2026)
- [DreamWAM: Beyond RGB Future Prediction for World Action Models](https://mlsanity.com/paper/2608.04996/) (2026)
- [LA4VLA: Learning to Act without Seeing via Language-Action Pretraining](https://mlsanity.com/paper/2606.27295/) (2026)
- [ABot-N1: Toward a General Visual Language Navigation Foundation Model](https://mlsanity.com/paper/2607.10383/) (2026)
- [WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory and In-Context Learning](https://mlsanity.com/paper/2607.18840/) (2026)
- [Data Pyramid for Embodied Manipulation: A Survey](https://mlsanity.com/paper/2607.24744/) (2026)
- [ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI](https://mlsanity.com/paper/2607.04426/) (2026)
- [HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone](https://mlsanity.com/paper/2607.25895/) (2026)
- [Riemann-1.0: An Embodied World Action Model for Physical AI](https://mlsanity.com/paper/2608.27033/) (2026)
- [ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training](https://mlsanity.com/paper/2609.00188/) (2026)
- [EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics](https://mlsanity.com/paper/2609.27308/) (2026)
- [Robostral Navigate](https://mlsanity.com/paper/2607.20785/) (2026)
- [Continue or Replan? Bernoulli-Continuation Policy Learning for Adaptive Horizon Execution](https://mlsanity.com/paper/2608.03483/) (2026)
- [Bridge-WA: Predicting Where and How the World Changes for Robotic Action](https://mlsanity.com/paper/2607.02195/) (2026)
- [TacPAC: Tactile Prediction and Real-Time Action Correction in World-Action Models for Contact-Rich Manipulation](https://mlsanity.com/paper/2609.05266/) (2026)
- [DLAM: Distributional Latent Actions with Temporal Constraints](https://mlsanity.com/paper/2607.27138/) (2026)
- [DyPES-VLA: Learning Shared Dynamics Priors and Embodiment-Specific Control for Cross-Embodiment Manipulation](https://mlsanity.com/paper/2608.06374/) (2026)
- [DELE-w0.5: Inferring Action from Future Latent State for Robotic Manipulation](https://mlsanity.com/paper/2608.22067/) (2026)
- [LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation](https://mlsanity.com/paper/2608.30935/) (2026)
- [Self-Adaptive VLA for Robust Robot Deployment](https://mlsanity.com/paper/2609.30092/) (2026)
- [DynaWM: A Base-VLA-Guided World Foundation Model for Moving-Object Manipulation](https://mlsanity.com/paper/2607.02604/) (2026)
- [LeapBot-WA: World-Anchor Action Models via Predictive Latent Alignments](https://mlsanity.com/paper/2607.23969/) (2026)
- [One Policy, Many Embodiments: Unified Camera-Centric Action Geometry Pre-training for Heterogeneous Embodied Manipulation](https://mlsanity.com/paper/2608.26058/) (2026)

## Abstract (arXiv)

Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented capabilities and limited generalization across tasks, environments, and robot embodiments. In this work, we study whether heterogeneous embodied decision-making problems can be unified within a single vision-language-action model. We present Qwen-VLA, a unified embodied foundation model that extends Qwen's vision-language modeling stack from perception, understanding, and reasoning to continuous action and trajectory generation through a DiT-based action decoder. Qwen-VLA is trained with a large-scale joint pretraining recipe over diverse data sources, including robotics manipulation trajectories, human egocentric demonstrations, synthetic simulation data, vision-and-language navigation data, trajectory-centric supervision, and auxiliary vision-language data. To support multiple robot platforms, we introduce embodiment-aware prompt conditioning, where robot-specific textual descriptions specify the current embodiment and control convention. We further cast manipulation, navigation, and trajectory prediction into a unified action-and-trajectory prediction framework, enabling transferable visual grounding, spatial reasoning, and continuous action generation across robot morphologies, task families, and environments. Experiments on manipulation, navigation, and trajectory-centric benchmarks show consistent multi-task performance and out-of-distribution generalization under variations in scene layout, background, lighting, object configuration, and robot embodiment. Qwen-VLA-Instruct achieves 97.9% on LIBERO, 73.7% on Simpler-WidowX, 86.1%/87.2% on RoboTwin-Easy/Hard, 69.0% OSR on R2R, 59.6% SR on RxR, 76.9% average OOD success in real-world ALOHA experiments, and 26.6% zero-shot success on DOMINO dynamic manipulation.