PrimitiveVLA: Learning Reusable Motion Primitives for Efficient and Generalizable Robotic Manipulation

• URL: http://arxiv.org/abs/2605.28634v1
• Date: Wed, 27 May 2026 15:41:18 GMT
• Title: PrimitiveVLA: Learning Reusable Motion Primitives for Efficient and Generalizable Robotic Manipulation
• Abstract summary: Vision-Language-Action (VLA) models offer a promising paradigm for generalist robotic policies.<n>We argue that these bottlenecks stem from the prevailing Direct Instruction-to-Control Mapping.<n>We propose PrimitiveVLA, a framework that shifts this paradigm toward a Primitive-Centric Disassemble & Assemble paradigm.
• Score: 50.8450025321217
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-Language-Action (VLA) models offer a promising paradigm for generalist robotic policies, yet their adaptation is hindered by data inefficiency and poor generalization. We argue that these bottlenecks stem from the prevailing Direct Instruction-to-Control Mapping, which forces models to memorize monolithic trajectories rather than reusable motion patterns, i.e., primitives. We propose PrimitiveVLA, a framework that shifts this paradigm toward a Primitive-Centric Disassemble & Assemble paradigm. Supported by a shared Multimodal Canonical Representation (MCR), PrimitiveVLA unifies two phases: (1) Fine-tuning-phase Disassembly, which uses an automated pipeline to disassemble demonstrations into reusable primitives; and (2) Inference-phase Assembly, which employs a VLM-based planner and an LLM-generated switch module for robust closed-loop execution. By disassembling tasks into reusable primitives, PrimitiveVLA enables VLA models to learn invariant motion patterns instead of task-specific trajectories. Extensive experiments show that our framework improves data efficiency and achieves superior zero-shot generalization across unseen and long-horizon tasks.

Related papers

• Decoupling the Declarative from the Procedural in Vision-Language-Action Models [65.22639791239932]
  Policy trained to clone a behavior from object-specific demonstrations must generalize beyond that object.<n>We propose w$2$VLA, a new Vision-Language-Action model with restructured information flow.<n>Unlike popular, state-of-the-art VLAs, we show that our modular approach successfully decouples knowledge representations.
  arXiv  Detail & Related papers  (2026-06-19T14:43:58Z)
• Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data [93.7685703383343]
  Vision-language models (VLMs) are powerful general-purpose reasoners, yet converting them into robot control policies is surprisingly difficult.<n>We argue that this gap can be bridged gradually with the right intermediate data.<n>We show that mixing task-relevant out-of-distribution ETC data with a small amount of action data enables the model to generalize to novel visual-language conditions.
  arXiv  Detail & Related papers  (2026-06-07T08:57:51Z)
• DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulation [12.935477248310674]
  We introduce DeMaVLA, a VLA foundation model for generalizable Deformable Manipulation.<n>DeMaVLA adopts a VLM backbone with an action expert and formulates continuous action generation using flow matching.<n>Experiments show that DeMaVLA achieves competitive performance on RoboTwin and strong real-world results on our household folding benchmark.
  arXiv  Detail & Related papers  (2026-05-29T13:20:08Z)
• $M^2$-VLA: Boosting Vision-Language Models for Generalizable Manipulation via Layer Mixture and Meta-Skills [25.17452377052361]
  Current Vision-Language-Action (VLA) models predominantly rely on end-to-end fine-tuning.<n>We propose $M2$-VLA, which demonstrates that a generalized VLM is able to serve as a powerful backbone for robotic manipulation directly.<n>To overcome this, we introduce the Mixture of Layers (MoL) strategy that selectively extracts task-critical information from dense semantic features.
  arXiv  Detail & Related papers  (2026-04-27T08:44:12Z)
• 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)
• OmniGuide: Universal Guidance Fields for Enhancing Generalist Robot Policies [75.40720507604647]
  Vision-language-action(VLA) models have shown great promise as generalist policies for a large range of relatively simple tasks.<n>We propose a flexible framework that improves VLA performance on such tasks by leveraging arbitrary sources of guidance.<n>We show how many kinds of guidance can be naturally expressed as differentiable energy functions with task-specific attractors and repellers located in 3D space.
  arXiv  Detail & Related papers  (2026-03-09T17:18:13Z)
• Reshaping Action Error Distributions for Reliable Vision-Language-Action Models [69.38615670891038]
  In robotic manipulation, vision-language-action (VLA) models have emerged as a promising paradigm for learning generalizable and scalable robot policies.<n>We focus on continuous-action VLA models and move beyond conventional MSE-based regression by reshaping action error distributions during training.<n>We evaluate our approaches across standard, few-shot, and noisy settings on multiple representative VLA architectures.
  arXiv  Detail & Related papers  (2026-02-04T05:37:09Z)
• HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policies [83.41714103649751]
  Development of embodied intelligence models depends on access to high-quality robot demonstration data.<n>We present HiMoE-VLA, a novel vision-language-action framework tailored to handle diverse robotic data with heterogeneity.<n>HiMoE-VLA demonstrates a consistent performance boost over existing VLA baselines, achieving higher accuracy and robust generalizations.
  arXiv  Detail & Related papers  (2025-12-05T13:21:05Z)
• MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization [30.871663465403625]
  We present MAPS, the first robust fine-tuning framework for Vision-Language-Action (VLA) models.<n>Through systematic analysis, we uncover an empirical order in which proximity constraints should be relaxed to balance stability and flexibility.<n> MAPS linearly schedules this relaxation, enabling visual encoders to stay close to their pretrained priors while action-oriented language layers adapt more freely.
  arXiv  Detail & Related papers  (2025-11-25T03:39:37Z)
• LLaDA-VLA: Vision Language Diffusion Action Models [23.653152301133925]
  Masked diffusion models, a paradigm distinct from autoregressive models, have begun to demonstrate competitive performance in text generation and multimodal applications.<n>We present LLaDA-VLA, the first Vision-Language-Diffusion-Action model built upon pretrained d-VLMs for robotic manipulation.
  arXiv  Detail & Related papers  (2025-09-08T17:45:40Z)
• Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models [48.15777554876988]
  Traditional alignment methods often require retraining large pretrained models.<n>We propose a novel textitResidual Alignment Model (textitRAM) that formalizes the alignment process as a type of importance sampling.<n>We develop a resampling algorithm with iterative token-level decoding to address the common first-token latency issue in comparable methods.
  arXiv  Detail & Related papers  (2025-05-26T08:53:02Z)

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.