Simple-to-Complex Structured Demonstrations for Vision-Language-Action Learning

• URL: http://arxiv.org/abs/2607.04591v1
• Date: Mon, 06 Jul 2026 01:38:43 GMT
• Title: Simple-to-Complex Structured Demonstrations for Vision-Language-Action Learning
• Abstract summary: Vision-Language-Action (VLA) models have demonstrated strong capabilities in robotic manipulation.<n>We identify demonstration organization as a fundamental yet overlooked aspect of imitation learning.<n>We propose a simple-to-complex structured demonstration collection strategy for VLA learning using a dual-arm robotic platform.
• Score: 9.340058165047717
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language-Action (VLA) models have demonstrated strong capabilities in robotic manipulation by integrating visual perception, language understanding, and robot action generation. Existing research has primarily focused on improving model architectures, training strategies, and dataset scale, while little attention has been paid to how demonstrations are collected and organized. We identify demonstration organization as a fundamental yet overlooked aspect of imitation learning, as it directly affects policy learning efficiency, training stability, and policy generalization. To address this gap, we propose a simple-to-complex structured demonstration collection strategy for VLA learning using a dual-arm robotic platform. Our approach systematically organizes data through three general principles: (i) decomposing complex manipulation tasks into progressively learnable sub-skills, (ii) standardizing the interaction environment to reduce unnecessary variability, and (iii) organizing demonstrations according to progressively increasing task complexity. This structured design enables VLA models to first acquire fundamental manipulation skills before learning increasingly complex task compositions, facilitating more effective learning of long-horizon manipulation tasks. We evaluate the proposed strategy on two representative robotic manipulation tasks: block grasping and sorting, and towel folding. Experimental results show consistent improvements in task success rate and training stability compared with the baseline method of directly collecting end-to-end complete task trajectories. These findings highlight demonstration organization as a previously underexplored but important factor in VLA learning and provide practical insights into efficient skill acquisition, scalable dataset construction, and long-horizon robotic manipulation.

Related papers

• AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding [55.535374902204296]
  AffordanceVLA is a unified framework that introduces structured affordance forecasting as a task-oriented intermediate representation.<n>We show that AffordanceVLA achieves strong performance across diverse manipulation scenarios.
  arXiv  Detail & Related papers  (2026-06-04T13:28:51Z)
• Build on Priors: Vision--Language--Guided Neuro-Symbolic Imitation Learning for Data-Efficient Real-World Robot Manipulation [4.118262876469644]
  We present a scalable neuro-symbolic framework that autonomously constructs symbolic planning domains and data-efficient control policies.<n>Our method segments demonstrations into skills and employs a Vision-Language Model (VLM) to classify skills.<n>Known controllers can be leveraged for real-world data augmentation by projecting a single demonstration onto other objects in the scene.
  arXiv  Detail & Related papers  (2026-04-04T15:17:59Z)
• CRAFT: Adapting VLA Models to Contact-rich Manipulation via Force-aware Curriculum Fine-tuning [46.57805525532354]
  Vision-Language-Action models can execute general instructions, but struggle with contact-rich manipulation tasks.<n>We introduce CRAFT, a force-aware curriculum fine-tuning framework to regulate vision and language embeddings during early training.<n>We show that CRAFT consistently improves task success, generalizes to unseen objects and novel task variations, and adapts effectively across diverse VLA architectures.
  arXiv  Detail & Related papers  (2026-02-13T02:28:21Z)
• Embodied Robot Manipulation in the Era of Foundation Models: Planning and Learning Perspectives [101.22313265304979]
  Recent advances in vision, language, and multimodal learning have accelerated progress in robotic foundation models.<n>This survey examines robot manipulation from an algorithmic perspective.<n>We organize recent learning-based approaches within a unified abstraction of high-level planning and low-level control.
  arXiv  Detail & Related papers  (2025-12-28T16:05:38Z)
• VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Models [9.376810354990079]
  We introduce VLA-OS, a unified VLA architecture series capable of various task planning paradigms.<n>We design a comprehensive suite of experiments across diverse object categories (rigid and deformable), visual modalities (2D and 3D), environments (simulation and real-world), and end-effectors (grippers and dexterous hands)
  arXiv  Detail & Related papers  (2025-06-21T03:07:48Z)
• Few-Shot Vision-Language Action-Incremental Policy Learning [55.07841353049953]
  Transformer-based robotic manipulation methods utilize multi-view spatial representations and language instructions to learn robot motion trajectories.<n>Existing methods lack the capability for continuous learning on new tasks with only a few demonstrations.<n>We develop a Task-prOmpt graPh evolutIon poliCy (TOPIC) to address these issues.
  arXiv  Detail & Related papers  (2025-04-22T01:30:47Z)
• Flex: End-to-End Text-Instructed Visual Navigation from Foundation Model Features [59.892436892964376]
  We investigate the minimal data requirements and architectural adaptations necessary to achieve robust closed-loop performance with vision-based control policies.<n>Our findings are synthesized in Flex (Fly lexically), a framework that uses pre-trained Vision Language Models (VLMs) as frozen patch-wise feature extractors.<n>We demonstrate the effectiveness of this approach on a quadrotor fly-to-target task, where agents trained via behavior cloning successfully generalize to real-world scenes.
  arXiv  Detail & Related papers  (2024-10-16T19:59:31Z)
• Exploring CausalWorld: Enhancing robotic manipulation via knowledge transfer and curriculum learning [6.683222869973898]
  This study explores a learning-based tri-finger robotic arm manipulating task, which requires complex movements and coordination among the fingers. By employing reinforcement learning, we train an agent to acquire the necessary skills for proficient manipulation. Two knowledge transfer strategies, fine-tuning and curriculum learning, were utilized within the soft actor-critic architecture.
  arXiv  Detail & Related papers  (2024-03-25T23:19:19Z)
• Visual Adversarial Imitation Learning using Variational Models [60.69745540036375]
  Reward function specification remains a major impediment for learning behaviors through deep reinforcement learning. Visual demonstrations of desired behaviors often presents an easier and more natural way to teach agents. We develop a variational model-based adversarial imitation learning algorithm.
  arXiv  Detail & Related papers  (2021-07-16T00:15:18Z)
• Automated Relational Meta-learning [95.02216511235191]
  We propose an automated relational meta-learning framework that automatically extracts the cross-task relations and constructs the meta-knowledge graph. We conduct extensive experiments on 2D toy regression and few-shot image classification and the results demonstrate the superiority of ARML over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2020-01-03T07:02:25Z)

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.