# VITA: Vision-to-Action Flow Matching Policy

arXiv: https://arxiv.org/abs/2507.13231 · HTML: https://mlsanity.com/paper/2507.13231/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 49 of its 59 references that are in the map.
- First posted on arXiv 17 Jul 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 30 of 49)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Building Normalizing Flows with Stochastic Interpolants](https://mlsanity.com/paper/2209.15571/) (2022)
- [Improving and generalizing flow-based generative models with minibatch optimal transport](https://mlsanity.com/paper/2302.00482/) (2023)
- [SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers](https://mlsanity.com/paper/2401.08740/) (2024)
- [What Matters in Learning from Offline Human Demonstrations for Robot Manipulation](https://mlsanity.com/paper/2108.03298/) (2021)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [Mean Flows for One-step Generative Modeling](https://mlsanity.com/paper/2505.13447/) (2025)
- [Pyramidal Flow Matching for Efficient Video Generative Modeling](https://mlsanity.com/paper/2410.05954/) (2024)
- [Diffusion Policy Policy Optimization](https://mlsanity.com/paper/2409.00588/) (2024)
- [ALOHA Unleashed: A Simple Recipe for Robot Dexterity](https://mlsanity.com/paper/2410.13126/) (2024)
- [FlowPolicy: Enabling Fast and Robust 3D Flow-based Policy via Consistency Flow Matching for Robot Manipulation](https://mlsanity.com/paper/2412.04987/) (2024)

## Built on by (most cited first, 25 of 25)

- [World Model for Robot Learning: A Comprehensive Survey](https://mlsanity.com/paper/2605.00080/) (2026)
- [AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models](https://mlsanity.com/paper/2511.14148/) (2025)
- [Action-to-Action Flow Matching](https://mlsanity.com/paper/2602.07322/) (2026)
- [Look, Focus, Act: Efficient and Robust Robot Learning via Human Gaze and Foveated Vision Transformers](https://mlsanity.com/paper/2507.15833/) (2025)
- [PolicyFlow: Policy Optimization with Continuous Normalizing Flow in Reinforcement Learning](https://mlsanity.com/paper/2602.01156/) (2026)
- [EfficientFlow: Efficient Equivariant Flow Policy Learning for Embodied AI](https://mlsanity.com/paper/2512.02020/) (2025)
- [Neuro-Symbolic Safety Guidance for Vision-Language-Action Models via Constrained Flow Matching](https://mlsanity.com/paper/2607.01378/) (2026)
- [Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition](https://mlsanity.com/paper/2511.09388/) (2025)
- [Sample from What You See: Visuomotor Policy Learning via Diffusion Bridge with Observation-Embedded Stochastic Differential Equation](https://mlsanity.com/paper/2512.07212/) (2025)
- [SA-VLA: Spatially-Aware Flow-Matching for Vision-Language-Action Reinforcement Learning](https://mlsanity.com/paper/2602.00743/) (2026)
- [MOTIF: Learning Action Motifs for Few-shot Cross-Embodiment Transfer](https://mlsanity.com/paper/2602.13764/) (2026)
- [From Noise to Intent: Anchoring Generative VLA Policies with Residual Bridges](https://mlsanity.com/paper/2604.21391/) (2026)
- [FLASH: Efficient Visuomotor Policy via Sparse Sampling](https://mlsanity.com/paper/2605.15492/) (2026)
- [Where Should Action Generation Begin? A Learnable Source Prior for Generative Robot Policies](https://mlsanity.com/paper/2606.17408/) (2026)
- [Agile-WAM: An Agile Tactile World Action Model for Contact-Rich Robot Control](https://mlsanity.com/paper/2609.20761/) (2026)
- [RAMAC: Multimodal Risk-Aware Offline Reinforcement Learning and the Role of Behavior Regularization](https://mlsanity.com/paper/2510.02695/) (2025)
- [TRACER: Texture-Robust Affordance Chain-of-Thought for Deformable-Object Refinement](https://mlsanity.com/paper/2601.20208/) (2026)
- [Temporal Policy: History-Initialized Action Generation for Robotic Learning from Demonstration](https://mlsanity.com/paper/2607.29482/) (2026)
- [Attention-DP3: Spatially Object-aware 3D Diffusion Policy via Geometry-aligned Attentional Conditioning](https://mlsanity.com/paper/2609.13318/) (2026)
- [Object-Centric Conditioning for Visuomotor Flow Matching](https://mlsanity.com/paper/2609.24155/) (2026)
- [The Gaussian Is Enough: Flow-Matching Priors Do Not Help When Fine-Tuning Large Behavior Models](https://mlsanity.com/paper/2609.27070/) (2026)
- [Zero-Shot Reactive Obstacle Avoidance for Generative Robot Policies](https://mlsanity.com/paper/2609.35231/) (2026)
- [DuoMind: Enabling Distributed Multi-Robot Coordination with Semantic Communication](https://mlsanity.com/paper/2610.02161/) (2026)
- [World-Calibrated Proposal-to-Action Flow for Vision-Language-Action Models](https://mlsanity.com/paper/2610.02323/) (2026)
- [Encoded but Not in Control: Revealing the Grounding Gap in Vision-Language Robot Policies](https://mlsanity.com/paper/2610.06235/) (2026)

## Abstract (arXiv)

Conventional flow matching and diffusion-based policies sample via iterative denoising from standard noise distributions (e.g., Gaussian), and require conditioning modules to repeatedly incorporate visual information during the generative process, incurring substantial time and memory overhead. To reduce the complexity, we develop VITA, VIsion-To-Action policy, a noise-free and conditioning-free flow matching policy learning framework that directly flows from visual representations to latent actions. Since the source of the flow is visually grounded, VITA eliminates the need for visual conditioning during generation. As expected, bridging vision and action is challenging, because actions are lower-dimensional, less structured, and sparser than visual representations; moreover, flow matching requires the source and target to have the same dimensionality. To overcome this, we introduce an action autoencoder that maps raw actions into a structured latent space aligned with visual latents, trained jointly with flow matching. To further prevent latent action space collapse during end-to-end training, we propose flow latent decoding, which anchors the latent generation process by backpropagating the action reconstruction loss through the flow matching ODE (ordinary differential equation) solving steps. We evaluate VITA on 9 simulation and 5 real-world tasks from ALOHA and Robomimic. VITA achieves 1.5x-2x faster inference compared to conventional methods with conditioning modules, while outperforming or matching state-of-the-art policies. Project page: https://ucd-dare.github.io/VITA/.