Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline

• URL: http://arxiv.org/abs/2602.22663v1
• Date: Thu, 26 Feb 2026 06:27:37 GMT
• Title: Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline
• Abstract summary: Vision-Language-Action (VLA) models have emerged as a generalist robotic agent.<n>Existing VLAs are hindered by excessive parameter scales, prohibitive pre-training requirements, and limited applicability to diverse embodiments.<n>We propose CEBench, a new benchmark spanning diverse embodiments in both simulation and the real world with consideration of domain randomization.
• Score: 38.41143967396976
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language-Action (VLA) models have emerged as a generalist robotic agent. However, existing VLAs are hindered by excessive parameter scales, prohibitive pre-training requirements, and limited applicability to diverse embodiments. To improve the practicality of VLAs, we propose a comprehensive benchmark and an improved baseline. First, we propose CEBench, a new benchmark spanning diverse embodiments in both simulation and the real world with consideration of domain randomization. We collect 14.4k simulated trajectories and 1.6k real-world expert-curated trajectories to support training on CEBench. Second, using CEBench as our testbed, we study three critical aspects of VLAs' practicality and offer several key findings. Informed by these findings, we introduce LLaVA-VLA, a lightweight yet powerful VLA designed for practical deployment on consumer-grade GPUs. Architecturally, it integrates a compact VLM backbone with multi-view perception, proprioceptive tokenization, and action chunking. To eliminate reliance on costly pre-training, LLaVA-VLA adopts a two-stage training paradigm including post-training and fine-tuning. Furthermore, LLaVA-VLA extends the action space to unify navigation and manipulation. Experiments across embodiments demonstrate the capabilities of generalization and versatility of LLaVA-VLA , while real-world mobile manipulation experiments establish it as the first end-to-end VLA model for mobile manipulation. We will open-source all datasets, codes, and checkpoints upon acceptance to foster reproducibility and future research.

Related papers

• DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA [72.9197085473598]
  DIAL is a framework bridging high-level decision making and low-level motor execution through a differentiable latent intent bottleneck.<n>A VLM-based System-2 performs latent world modeling by latent visual foresight within the VLM's native feature space.<n>A lightweight System-1 policy then decodes this predicted intent together with the current observation into precise robot actions.
  arXiv  Detail & Related papers  (2026-03-31T15:02:27Z)
• SimVLA: A Simple VLA Baseline for Robotic Manipulation [46.38114519538192]
  Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robotic manipulation.<n>We introduce SimVLA, a streamlined baseline designed to establish a transparent reference point for VLA research.
  arXiv  Detail & Related papers  (2026-02-20T14:04:27Z)
• VLANeXt: Recipes for Building Strong VLA Models [95.4552662536287]
  Vision-Language-Action models (VLAs) emerged, leveraging strong visual and language understanding for policy learning.<n>Many groups have proposed their own VLA models, but inconsistencies in training protocols and evaluation settings make it difficult to identify which design choices truly matter.<n>We will release a unified, easy-to-use framework that serves as a common platform for the community to reproduce our findings.
  arXiv  Detail & Related papers  (2026-02-20T09:26:17Z)
• DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving [52.63591791507895]
  We propose textbfDriveVLA-W0, a training paradigm that employs world modeling to predict future images.<n>This task generates a dense, self-supervised signal that compels the model to learn the underlying dynamics of the driving environment.<n>Experiments on the NAVSIM v1/v2 benchmark and a 680x larger in-house dataset demonstrate that DriveVLA-W0 significantly outperforms BEV and VLA baselines.
  arXiv  Detail & Related papers  (2025-10-14T17:59:47Z)
• X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model [62.21943953611646]
  Vision-Language-Action models rely on effective training across diverse robotic platforms.<n>We propose a novel Soft Prompt approach with minimally added parameters.<n>We show that our 0.9B instantiation-X-VLA-0.9B simultaneously achieves SOTA performance over a sweep of benchmarks.
  arXiv  Detail & Related papers  (2025-10-11T16:20:17Z)
• Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends [11.678954304546988]
  Vision-language-action (VLA) models extend vision-language models (VLM)<n>This paper reviews post-training strategies for VLA models through the lens of human motor learning.
  arXiv  Detail & Related papers  (2025-06-26T03:06:57Z)
• TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation [32.406783380729024]
  Vision-Language-Action (VLA) models have shown remarkable potential in visuomotor control and instruction comprehension through end-to-end learning processes.<n>Current VLA models face significant challenges: they are slow during inference and require extensive pre-training on large amounts of robotic data.<n>We introduce a new family of compact vision-language-action models, called TinyVLA, which offers two key advantages over existing VLA models.
  arXiv  Detail & Related papers  (2024-09-19T07:10:18Z)
• OpenVLA: An Open-Source Vision-Language-Action Model [131.74098076670103]
  We introduce OpenVLA, an open-source VLA trained on a diverse collection of 970k real-world robot demonstrations. OpenVLA shows strong results for generalist manipulation, outperforming closed models such as RT-2-X (55B) by 16.5% in absolute task success rate. We release model checkpoints, fine-tuning notebooks, and our PyTorch with built-in support for training VLAs at scale on Open X-Embodiment datasets.
  arXiv  Detail & Related papers  (2024-06-13T15:46:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.