mlsanityData to 7 Oct 2026

π0-EqM: Equilibrium Matching for Closed-Loop Vision-Language-Action Control

arXiv 2605.23128 ↗First posted 22 May 2026cs.ROcited by 3

On the map: Vision-language-action models → Efficient VLA inference and adaptation

also in 1 more
Abstract (arXiv)

Currently, Vision-Language-Action (VLA) models have become the most adopted paradigm for robotic manipulation for its great potential for task generalization. While most generative flow-matching action decoders for VLA control are often deployed with fixed sampling horizons, limiting state-dependent compute and temporal reuse across control cycles. We present π0-EqM, which replaces the flow-matching expert in π0 with an Equilibrium Matching (EqM) decoder while leaving the upstream VLA stack unchanged. Under a matched 300-step budget, π0-EqM improves RoboTwin average success from 40.4% to 50.2% across 19 tasks and remains competitive on LIBERO, with its clearest gain on LIBERO-10 (87.0%). Two threshold scans reveal a task-dependent non-monotonic relation between residual and success, which we term the stationarity--executability gap. The results suggest that inference depth in iterative VLA control is part of policy design and introduce an energy-based VLA perspective that may inform future work on composable action generation across tasks and embodiments.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Efficient VLA inference and adaptation, one of 13 directions in Vision-language-action models. Builds on 13 of its 16 references that are in the map. First posted on arXiv 22 May 2026.

Builds on

13 of 16 references.

References · 13

  1. 2022Flow Matching for Generative Modelingcited by 5,426
  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. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  8. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  9. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  10. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 477
  11. 2021Implicit Behavioral Cloningcited by 442
  12. 2025Equilibrium Matching: Generative Modeling with Implicit Energy-Based Modelscited by 18
1 more
  1. 2026Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Controlcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Orca: The World is in Your Mindcited by 6
  2. 2026DriftingVLA: Native One-Step Vision-Language-Action Generation via Per-Dimension Temporal Driftingcited by 2
  3. 2026DynaWM: A Base-VLA-Guided World Foundation Model for Moving-Object Manipulationcited by 0

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. 2026Fewer Steps, Better Actions: Rethinking Flow-Matching Inference for VLA Policies
  3. 2026ProbeFlow: Training-Free Adaptive Flow Matching for Vision-Language-Action Models
  4. 2026Decoupled Early Exits for Task-Dependent Compute Allocation in Flow-Matching VLAs
  5. 2026Let It Be Simple: One-Step Action Generation for Vision-Language-Action Models
  6. 2026ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models
  7. 2025E0: Enhancing Generalization and Fine-Grained Control in VLA Models via Tweedie Discrete Diffusion
  8. 2025CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding