AC-VLA: Robust Out-of-Distribution Action Execution via Compositional Learning

• URL: http://arxiv.org/abs/2607.15714v1
• Date: Fri, 17 Jul 2026 07:51:03 GMT
• Title: AC-VLA: Robust Out-of-Distribution Action Execution via Compositional Learning
• Abstract summary: Vision-Language-Action (VLA) models excel at end-to-end robotic manipulation but struggle with out-of-distribution (OOD) generalization.<n>We identify two mutually reinforcing modes: emphtrajectory overfitting, where models overfit to holistic trajectory patterns rather than compositional sub-skill semantics; and emphperceptual shortcut, where action tokens over-rely on wrist-view textures at the expense of global spatial grounding.<n>We introduce textbfAC-VLA, a plug-and-play Action Compositional learning
• Score: 52.47988016454267
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language-Action (VLA) models excel at end-to-end robotic manipulation but struggle with out-of-distribution (OOD) generalization when familiar sub-tasks are recombined in unseen configurations. We identify two mutually reinforcing failure modes: \emph{trajectory overfitting}, where models overfit to holistic trajectory patterns rather than compositional sub-skill semantics; and \emph{perceptual shortcut}, where action tokens over-rely on wrist-view textures at the expense of global spatial grounding. To address both, we introduce \textbf{AC-VLA}, a plug-and-play Action Compositional learning framework comprising two architecture-agnostic components: \textbf{(i)} a compositional learning module that uses an LLM-driven instruction decomposer and a proprioceptive trajectory aligner to generate dense sub-task supervision, followed by mixed training on complete demonstrations and decomposed data to endow the model with compositional generalization; and \textbf{(ii)} a state-conditioned asymmetric masking strategy that suppresses wrist-view inputs during closed-gripper phases, enforcing global semantic grounding. All components are architectural modification-free and directly integrable into any VLA backbone. Instantiated on $π_{0.5}$ and evaluated on LIBERO and LIBERO-OOD benchmarks, AC-VLA achieves a ~28% absolute improvement on compositional OOD tasks while maintaining near-perfect in-distribution performance.

Related papers

• Dynamics-Aware Meta-Imitation for Generalization to Unseen Robotic Manipulation [17.382238044141783]
  We propose a framework for learning skills from demonstrations for robots.<n>By integrating meta-learning to construct a shared skill space, DAMI equips agents for rapid adaptation to novel tasks.<n>Our approach outperforms state-of-the-art baselines regarding direct inference on seen tasks and adaptation to unseen tasks.
  arXiv  Detail & Related papers  (2026-07-17T11:50:03Z)
• Bridging Semantics and Kinematics: A Modular Framework for Zero-Shot Robotic Manipulation [0.6927055673104934]
  The architecture bridges the gap between high-level reasoning and low-level kinematics by decomposing the vision-action pipeline into three stages: visual perception, semantic interpretation, and task execution.<n>The framework is evaluated across two zero-shot experimental setups: unconstrained open-world sequential manipulation and dense relational spatial reasoning.
  arXiv  Detail & Related papers  (2026-06-22T11:01:56Z)
• 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)
• Libra-VLA: Achieving Learning Equilibrium via Asynchronous Coarse-to-Fine Dual-System [15.427164345561417]
  Vision-Language-Action (VLA) models are a promising paradigm for generalist robotic manipulation.<n>We introduce Libra-VLA, a novel Coarse-to-Fine Dual-System VLA architecture.<n>We show that our approach offers a scalable, robust, and responsive solution for open-world manipulation.
  arXiv  Detail & Related papers  (2026-04-27T19:02:46Z)
• SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation [65.6201974979119]
  We propose SemanticVLA, a novel VLA framework that performs Semantic-Hierarchical Sparsification and Enhancement for Efficient Robotic Manipulation.<n>SemanticVLA surpasses OpenVLA on LIBERO benchmark by 21.1% in success rate, while reducing training cost and inference latency by 3.0-fold and 2.7-fold.
  arXiv  Detail & Related papers  (2025-11-13T17:24:37Z)
• CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning [80.18781219542016]
  Continual Learning (CL) empowers AI models to continuously learn from sequential task streams.<n>Recent parameter-efficient fine-tuning (PEFT)-based CL methods have garnered increasing attention due to their superior performance.<n>We propose Cross-subspace Knowledge Alignment and Aggregation (CKAA) to enhance robustness against misleading task-ids.
  arXiv  Detail & Related papers  (2025-07-13T03:11:35Z)
• How PARTs assemble into wholes: Learning the relative composition of images [25.06788919709452]
  spatial-aware pretext tasks have been actively explored in self-supervised learning.<n> grid-based approaches fall short of capturing the fluid and continuous nature of real-world object compositions.<n>We introduce PART, a self-supervised learning approach that leverages continuous relative transformations between off-grid patches.
  arXiv  Detail & Related papers  (2025-06-04T08:12:18Z)
• Semantic-Aligned Learning with Collaborative Refinement for Unsupervised VI-ReID [82.12123628480371]
  Unsupervised person re-identification (USL-VI-ReID) seeks to match pedestrian images of the same individual across different modalities without human annotations for model learning.<n>Previous methods unify pseudo-labels of cross-modality images through label association algorithms and then design contrastive learning framework for global feature learning.<n>We propose a Semantic-Aligned Learning with Collaborative Refinement (SALCR) framework, which builds up objective for specific fine-grained patterns emphasized by each modality.
  arXiv  Detail & Related papers  (2025-04-27T13:58:12Z)
• USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval [115.28586222748478]
  Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant to the given query from the other modality. Existing approaches typically suffer from two major limitations.
  arXiv  Detail & Related papers  (2023-01-17T12:42:58Z)

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.