mlsanityData to 7 Oct 2026

FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies

arXiv 2509.04996 ↗First posted 5 Sep 2025cs.ROcited by 56

On the map: Vision-language-action models → Generalist VLA models and benchmarks

Abstract (arXiv)

Developing efficient Vision-Language-Action (VLA) policies is crucial for practical robotics deployment, yet current approaches face prohibitive computational costs and resource requirements. Existing diffusion-based VLA policies require multi-billion-parameter models and massive datasets to achieve strong performance. We tackle this efficiency challenge with two contributions: intermediate-modality fusion, which reallocates capacity to the diffusion head by pruning up to 50% of LLM layers, and action-specific Global-AdaLN conditioning, which cuts parameters by 20% through modular adaptation. We integrate these advances into a novel 950 M-parameter VLA called FLOWER. Pretrained in just 200 H100 GPU hours, FLOWER delivers competitive performance with bigger VLAs across 190 tasks spanning ten simulation and real-world benchmarks and demonstrates robustness across diverse robotic embodiments. In addition, FLOWER achieves a new SoTA of 4.53 on the CALVIN ABC benchmark. Demos, code and pretrained weights are available at https://intuitive-robots.github.io/flowervla/.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Placed in Generalist VLA models and benchmarks, one of 13 directions in Vision-language-action models. Builds on 62 of its 67 references that are in the map. First posted on arXiv 5 Sep 2025.

Builds on

62 of 67 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better29 May
  2. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success27 Feb
  3. 2024What Matters in Building Vision-Language-Action Models for Generalist Robots18 Dec
  4. 2024π0: A Vision-Language-Action Flow Model for General Robot Control31 Oct
  5. 2024Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation10 Oct
  6. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation19 Sep
  7. 2024OpenVLA: An Open-Source Vision-Language-Action Model13 Jun
  8. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul

Other references · 54

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Denoising Diffusion Implicit Modelscited by 9,655
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2022Scalable Diffusion Models with Transformerscited by 5,931
  5. 2022Flow Matching for Generative Modelingcited by 5,426
  6. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  7. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  8. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  9. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  10. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  11. 2020GLU Variants Improve Transformercited by 1,724
  12. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
38 more
  1. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  2. 2019Root Mean Square Layer Normalizationcited by 1,425
  3. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  4. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  5. 2022Building Normalizing Flows with Stochastic Interpolantscited by 964
  6. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  7. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  8. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 643
  9. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  10. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 564
  11. 2024Scaling and evaluating sparse autoencoderscited by 530
  12. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
  13. 2023Florence-2: Advancing a Unified Representation for a Variety of Vision Taskscited by 403
  14. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 377
  15. 2023Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulationcited by 353
  16. 2023Vision-Language Foundation Models as Effective Robot Imitatorscited by 344
  17. 2024Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representationscited by 279
  18. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representationscited by 278
  19. 2020Query-Key Normalization for Transformerscited by 266
  20. 2023Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Modelscited by 264
  21. 2023Goal-Conditioned Imitation Learning using Score-based Diffusion Policiescited by 229
  22. 2025SmolVLM: Redefining small and efficient multimodal modelscited by 226
  23. 2015Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hourscited by 208
  24. 2024Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulationcited by 159
  25. 2024Data Scaling Laws in Imitation Learning for Robotic Manipulationcited by 144
  26. 2024Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goalscited by 131
  27. 2024DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Executioncited by 116
  28. 2020One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Controlcited by 114
  29. 2024Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviationcited by 108
  30. 2023On Bringing Robots Homecited by 101
  31. 2024BAKU: An Efficient Transformer for Multi-Task Policy Learningcited by 80
  32. 2024The Ingredients for Robotic Diffusion Transformerscited by 72
  33. 2024Riemannian Flow Matching Policy for Robot Motion Learningcited by 61
  34. 2024Affordance-based Robot Manipulation with Flow Matchingcited by 54
  35. 2024Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrationscited by 51
  36. 2024Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learningcited by 46
  37. 2024Robot Utility Models: General Policies for Zero-Shot Deployment in New Environmentscited by 43
  38. 2018Hardware Conditioned Policies for Multi-Robot Transfer Learningcited by 42

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 13; 2026: 43.

56 papers.

Sort:

By area:

  1. 2026Causal World Modeling for Robot Controlcited by 289
  2. 2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Modelcited by 285
  3. 2025mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAscited by 133
  4. 2026ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learningcited by 94
  5. 2026Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Executioncited by 42
  6. 2025A Survey on Efficient Vision-Language-Action Modelscited by 34
  7. 2026StarVLA-α: Reducing Complexity in Vision-Language-Action Systemscited by 27
  8. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Surveycited by 25
  9. 2026QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Modelscited by 25
  10. 2025AVA-VLA: Improving Vision-Language-Action models with Active Visual Attentioncited by 22
  11. 2026HoloBrain-0 Technical Reportcited by 20
  12. 2026FASTER: Rethinking Real-Time Flow VLAscited by 20
38 more
  1. 2026CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansioncited by 14
  2. 2026VLANeXt: Recipes for Building Strong VLA Modelscited by 12
  3. 2025HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policiescited by 10
  4. 2026Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performancecited by 9
  5. 2026CORAL: Scalable Multi-Task Robot Learning via LoRA Expertscited by 8
  6. 2026LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Modelscited by 8
  7. 2025Robotic VLA Benefits from Joint Learning with Motion Image Diffusioncited by 7
  8. 2025ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL Problemscited by 6
  9. 2026AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulationcited by 6
  10. 2026Green-VLA: Staged Vision-Language-Action Model for Generalist Robotscited by 6
  11. 2026AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Modelscited by 6
  12. 2026PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interactioncited by 6
  13. 2025PhysiAgent: An Embodied Agent Framework in Physical Worldcited by 5
  14. 2025MetaVLA: Unified Meta Co-training For Efficient Embodied Adaptioncited by 4
  15. 2025EfficientFlow: Efficient Equivariant Flow Policy Learning for Embodied AIcited by 4
  16. 2026OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelismcited by 4
  17. 2026CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policiescited by 4
  18. 2026ChunkFlow: Towards Continuity-Consistent Chunked Policy Learningcited by 4
  19. 2026Tri-Info: Generalizable, Interpretable Failure Prediction for VLA Models via Information Theorycited by 3
  20. 2025SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understandingcited by 2
  21. 2026Neural Implicit Action Fields: From Discrete Waypoints to Continuous Functions for Vision-Language-Action Modelscited by 2
  22. 2026From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulationcited by 2
  23. 2026QuoVLA: Quotient Space for Vision-Language-Action Modelscited by 2
  24. 2026PearlVLA: Progressive Embodied Action-Plan Refinement in Latent Spacecited by 2
  25. 2026IVRA: Improving Visual-Token Relations for Robot Action Policy with Training-Free Hint-Based Guidancecited by 1
  26. 2026Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action Modelscited by 1
  27. 2026ERQA-Plus: A Diagnostic Benchmark for Reasoning in Embodied AIcited by 1
  28. 2026Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Thinkcited by 1
  29. 2026ASCII Art Turns LLMs into VLA Controllerscited by 1
  30. 2026WOLF-VLA: Whole-Body Humanoid Optimal Locomotion Framework for Vision-Language-Action Learningcited by 1
  31. 2026hint2: Hierarchical World Models for Inference-Time Temporal Logic Guidancecited by 1
  32. 2025Freeze, Share, Shrink: Rethinking the Action Backbone in Diffusion Policiescited by 0
  33. 2026MPCoT: Reward-Guided Multi-Path Latent Reasoning for Test-Time Scalable Vision-Language-Actioncited by 0
  34. 2026LEEVLA: Seeing What Matters in Latent Environment Evolution for Vision-Language-Actioncited by 0
  35. 2026Semantic Anchoring for Robotic Action Representationscited by 0
  36. 2026SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulationcited by 0
  37. 2026StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Modelscited by 0
  38. 2026GeomVLA: Unifying Scene, Motion, and Action in 3Dcited by 0

50 most cited of 56 All 56 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model
  2. 2026Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline
  3. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
  4. 2025dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought
  5. 2026Decoupled Early Exits for Task-Dependent Compute Allocation in Flow-Matching VLAs
  6. 2025NanoVLA: Routing Decoupled Vision-Language Understanding for Nano-sized Generalist Robotic Policies
  7. 2026CoRE-VLA: Towards Scalable and Robust Vision-Language-Action Modeling via Conditional Routing of Experts
  8. 2025Towards Deploying VLA without Fine-Tuning: Plug-and-Play Inference-Time VLA Policy Steering via Embodied Evolutionary Diffusion