AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models

• URL: http://arxiv.org/abs/2603.08519v1
• Date: Mon, 09 Mar 2026 15:52:48 GMT
• Title: AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models
• Abstract summary: Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation.<n>Current paradigms rely on coarse, high-level task instructions during supervised fine-tuning.<n>We propose method, the first subtask-aware VLA framework integrated with a scalable offline post-training pipeline.
• Score: 9.608633915316252
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation. The execution of complex multi-step behaviors in VLA models can be improved by robust instruction grounding, a critical component for effective control. However, current paradigms predominantly rely on coarse, high-level task instructions during supervised fine-tuning. This instruction grounding gap leaves models without explicit intermediate guidance, leading to severe compounding errors in long-horizon tasks. Therefore, bridging this instruction gap and providing scalable post-training for VLA models is urgent. To tackle this problem, we propose \method, the first subtask-aware VLA framework integrated with a scalable offline post-training pipeline. Our framework leverages a large language model to decompose high-level demonstrations into fine-grained atomic subtasks. This approach utilizes a pretrained predictive world model to score candidate action chunks against subtask goals in the latent space, mitigating error accumulation while significantly improving long-horizon robustness. Furthermore, this approach enables highly efficient Group Relative Policy Optimization without the prohibitive expenses associated with online rollouts on physical robots. Extensive simulations validate that our AtomVLA maintains strong robustness under perturbations. When evaluated against fundamental baseline models, it achieves an average success rate of 97.0\% on the LIBERO benchmark and 48.0\% on the LIBERO-PRO benchmark. Finally, experiments conducted in the real world using the Galaxea R1 Lite platform confirm its broad applicability across diverse tasks, especially long-horizon tasks. All datasets, checkpoints, and code will be released to the public domain following the acceptance of this work for future research.

Related papers

• Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models [120.24139942108405]
  Scaling robot data is crucial for building generalist Vision-Language-Action (VLA) models.<n>Under a fixed robot-data budget, continued pre-training must turn limited trajectories into transferable visual-action knowledge.<n>We propose VLAct, a VLA-oriented VLM backbone trained on broad, heterogeneous, multi-embodiment robot data.
  arXiv  Detail & Related papers  (2026-08-27T17:59:40Z)
• Beyond Flat Policies: Hierarchical Post-Training for Embodied Agents in Robotic Manipulation [34.87301719899886]
  Vision-language-action (VLA) models have demonstrated remarkable capabilities in robotic manipulation by leveraging pretrained vision-language models.<n>Existing post-training methods predominantly optimize VLA models as flat policies, making it difficult to explicitly model task progression and perform robust long-horizon manipulation.<n>We propose Hierarchical Robotic Control (HiRoC), a hierarchical post-training framework that decouples high-level task planning from low-level action execution.
  arXiv  Detail & Related papers  (2026-08-06T13:07:56Z)
• 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)
• VLA-IAP: Training-Free Visual Token Pruning via Interaction Alignment for Vision-Language-Action Models [27.12266806191131]
  Vision-Language-Action (VLA) models have rapidly advanced embodied intelligence, enabling robots to execute complex, instruction-driven tasks.<n>Current approaches often prune visually sparse yet structurally critical regions that support manipulation, leading to unstable behavior during early task phases.<n>Our proposed textbftraining-free method, VLA-IAP (Interaction-Aligned Pruning), introduces a geometric prior mechanism to preserve structural anchors and a dynamic scheduling strategy.
  arXiv  Detail & Related papers  (2026-03-24T09:33:05Z)
• AnoleVLA: Lightweight Vision-Language-Action Model with Deep State Space Models for Mobile Manipulation [2.2357163812666716]
  Vision-Language-Action models (VLAs) have demonstrated strong performance for this task.<n>But their deployment in resource-constrained environments remains challenging because of the computational cost of standard transformer backbones.<n>We propose AnoleVLA, a lightweight VLA that uses a deep state space model to process multimodal sequences efficiently.
  arXiv  Detail & Related papers  (2026-03-16T09:57:45Z)
• See, Plan, Rewind: Progress-Aware Vision-Language-Action Models for Robust Robotic Manipulation [59.07792608884117]
  We introduce See, Plan, Rewind (SPR), a progress-aware vision-language-action framework.<n>SPR operates through a continuous core cycle, Seeing the current state and upcoming milestone, Planning a trajectory towards the next 2D waypoint, and Rewinding to a recoverable state upon failure.<n>SPR achieves state-of-the-art robustness with the smallest performance drop, surpassing OpenVLA-OFT and UniVLA.
  arXiv  Detail & Related papers  (2026-03-10T07:22:51Z)
• DexHiL: A Human-in-the-Loop Framework for Vision-Language-Action Model Post-Training in Dexterous Manipulation [14.050551792714083]
  Human-in-the-Loop (HiL) learning has proven to be a powerful mechanism for refining robot policies.<n>We present DexHiL, the first integrated arm-hand human-in-the-loop framework for dexterous VLA models.
  arXiv  Detail & Related papers  (2026-03-10T02:55:27Z)
• LiLo-VLA: Compositional Long-Horizon Manipulation via Linked Object-Centric Policies [54.150202739999806]
  LiLo-VLA is a modular framework capable of zero-shot modularity to novel long-horizon tasks without ever being trained on them.<n>We introduce a 21-task simulation benchmark consisting of two challenging suites: LIBERO-Long++ and Ultra-Long.<n>In these simulations, LiLo-VLA achieves a 69% average success rate, outperforming Pi0.5 by 41% and OpenVLA-OFT by 67%.
  arXiv  Detail & Related papers  (2026-02-25T03:33:39Z)
• 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)
• Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
  We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
  arXiv  Detail & Related papers  (2025-12-02T14:42:54Z)
• Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance [63.33213516925946]
  We introduce textbfAlign-Then-stEer (textttATE), a novel, data-efficient, and plug-and-play adaptation framework.<n>Our work presents a general and lightweight solution that greatly enhances the practicality of deploying VLA models to new robotic platforms and tasks.
  arXiv  Detail & Related papers  (2025-09-02T07:51:59Z)
• Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success [100.226572152954]
  We present an optimized fine-tuning recipe for vision-language-action models (VLAs)<n>Our recipe boosts OpenVLA's average success rate across four task suites from 76.5% to 97.1% while increasing action generation throughput by 26$times$.<n>In real-world evaluations, our fine-tuning recipe enables OpenVLA to successfully execute dexterous, high-frequency control tasks on a bimanual ALOHA robot.
  arXiv  Detail & Related papers  (2025-02-27T00:30:29Z)

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.