Robotics Research Hub

evaluation

12 papers

Evaluation methodologies and benchmarks.

ar-vr evaluation generation manipulation diffusion-policy assembly imitation-learning benchmarking vla

Papers

Sorted by year (newest first)
PhAIL: A Real-Robot VLA Benchmark and Distributional Methodology

PhAIL: A Real-Robot VLA Benchmark and Distributional Methodology

Sergey Arkhangelskiy · arXiv preprint · May 2026

Real-world evaluation of vision-language-action (VLA) policies still rests on binary success rate at a fixed timeout with N <= 25 rollouts per condition, almost always without confidence intervals or

benchmarking vla manipulation evaluation
PDF Intermediate
No code repo Code updated: May 2026

Suggested Learning Path

Read these papers in order to build expertise in evaluation.

  1. 1
    Co-VLA: Coordination-Aware Structured Action Modeling for Dual-Arm Vision-Language-Action Systems

    Yandong Wang, Jiaqian Yu et al. · 2026

  2. 2
    Co-VLA: Coordination-Aware Structured Action Modeling for Dual-Arm Vision-Language-Action Systems

    Yandong Wang, Jiaqian Yu et al. · 2026

  3. 3
    Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think

    Gia-Binh Nguyen, Trong-Bao Ho et al. · 2026

  4. 4
    Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think

    Gia-Binh Nguyen, Trong-Bao Ho et al. · 2026

  5. 5
    Frequency-Aware Flow Matching for Continuous and Consistent Robotic Action Generation

    Jianing Guo, Fangzheng Chen et al. · 2026

  6. 6
    Frequency-Aware Flow Matching for Continuous and Consistent Robotic Action Generation

    Jianing Guo, Fangzheng Chen et al. · 2026

…and 6 more papers.