mlsanityData to 7 Oct 2026

EquiVLA: A General Framework for Rotationally Equivariant Vision-Language-Action Models

arXiv 2606.19784 ↗First posted 18 Jun 2026cs.ROcited by 1

On the map: Vision-language-action models → 3D and spatial-aware VLA

also in 1 more
Abstract (arXiv)

Vision-Language-Action (VLA) models have emerged as a powerful paradigm for generalist robot manipulation, yet they lack geometric inductive biases: policies trained at specific orientations require substantially more data to generalize across rotational configurations. We present textscEquiVLA, the first general framework for end-to-end SO(2)-equivariant VLA models, applicable to any architecture coupling a frozen vision-language backbone with a flow-matching Diffusion Transformer action head. textscEquiVLA introduces textscEquiPerceptor, which produces approximately SO(2)-equivariant visual representations from frozen ViT features; and textscEquiActor, an exactly SO(2)-equivariant flow-matching Diffusion Transformer action head. Together, they establish an approximate SO(2) equivariance chain from camera observations to predicted action sequences. Instantiated on GR00T~N1.5 and evaluated across four LIBERO suites, CALVIN ABCD→D, and five real-robot tasks on Mobile ALOHA, textscEquiVLA achieves 92.6% average success on LIBERO (vs. 78.1% baseline), an average sequence length of 4.03 on CALVIN (vs. 3.45), and improves real-robot success from 54% to 72%.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in 3D and spatial-aware VLA, one of 13 directions in Vision-language-action models. Builds on 34 of its 37 references that are in the map. First posted on arXiv 18 Jun 2026.

Builds on

34 of 37 references.

References · 34

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  3. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  4. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  5. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  6. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  7. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,653
  8. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  9. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  10. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  11. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 844
  12. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
22 more
  1. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 669
  2. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 564
  3. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 507
  4. 2019General E(2)-Equivariant Steerable CNNscited by 441
  5. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 411
  6. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 377
  7. 2021Frame Averaging for Invariant and Equivariant Network Designcited by 166
  8. 2022What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Datacited by 137
  9. 2021Provably Strict Generalisation Benefit for Equivariant Modelscited by 90
  10. 2022SO(2)-Equivariant Reinforcement Learningcited by 79
  11. 2023FAENet: Frame Averaging Equivariant GNN for Materials Modelingcited by 72
  12. 2024EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learningcited by 72
  13. 2024Equivariant Diffusion Policycited by 61
  14. 2024Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learningcited by 46
  15. 2022Equivariant Transporter Networkcited by 44
  16. 2024ET-SEED: Efficient Trajectory-Level SE(3) Equivariant Diffusion Policycited by 24
  17. 2022SEIL: Simulation-augmented Equivariant Imitation Learningcited by 22
  18. 2025Large Language-Geometry Model: When LLM meets Equivariancecited by 10
  19. 2024Approximate Equivariance in Reinforcement Learningcited by 9
  20. 2025EquAct: An SE(3)-Equivariant Multi-Task Transformer for Open-Loop Robotic Manipulationcited by 8
  21. 2025A Practical Guide for Incorporating Symmetry in Diffusion Policycited by 4
  22. 2025Eq.Bot: Enhance Robotic Manipulation Learning via Group Equivariant Canonicalizationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026SAVLA: Symmetry-Aware Vision-Language-Action Models for Robotic Manipulationcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025E0: Enhancing Generalization and Fine-Grained Control in VLA Models via Tweedie Discrete Diffusion
  2. 2026G3VLA: Geometric inductive bias for Vision-Language-Action Models
  3. 2026RotVLA: Rotational Latent Action for Vision-Language-Action Model
  4. 2026AWM-VLA: AlignedWorld Modeling for Efficient and Explainable Vision-Language-Action Policies
  5. 2026π0-EqM: Equilibrium Matching for Closed-Loop Vision-Language-Action Control
  6. 2026Decoupling Vision, Language, and Action for Efficient Multi-Task Robot Policies
  7. 2025XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations
  8. 2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model