DexHiL: A Human-in-the-Loop Framework for Vision-Language-Action Model Post-Training in Dexterous Manipulation

• URL: http://arxiv.org/abs/2603.09121v1
• Date: Tue, 10 Mar 2026 02:55:27 GMT
• Title: DexHiL: A Human-in-the-Loop Framework for Vision-Language-Action Model Post-Training in Dexterous Manipulation
• Abstract summary: 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.
• Score: 14.050551792714083
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While Vision-Language-Action (VLA) models have demonstrated promising generalization capabilities in robotic manipulation, deploying them on specific and complex downstream tasks still demands effective post-training. In parallel, Human-in-the-Loop (HiL) learning has proven to be a powerful mechanism for refining robot policies. However, extending this paradigm to dexterous manipulation remains challenging: multi-finger control is high-dimensional, contact-intensive, and exhibits execution distributions that differ markedly from standard arm motions, leaving existing dexterous VLA systems limited in reliability and adaptability. We present DexHiL, the first integrated arm-hand human-in-the-loop framework for dexterous VLA models, enabling coordinated interventions over the arm and the dexterous hand within a single system. DexHiL introduces an intervention-aware data sampling strategy that prioritizes corrective segments for post-training, alongside a lightweight teleoperation interface that supports instantaneous human corrections during execution. Real-robot experiments demonstrate that DexHiL serves as an effective post-training framework, yielding a substantial performance leap, outperforming standard offline-only fine-tuning baselines by an average of 25% in success rates across distinct tasks. Project page: https://chenzhongxi-sjtu.github.io/dexhil/

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)
• Dexora: Open-source VLA for High-DoF Bimanual Dexterity [97.98653150757526]
  We introduce Dexora, the first open-source VLA system that targets dual-arm, dual-hand high-DoF manipulation.<n>We design a hybrid teleoperation pipeline that decouples gross arm kinematics from fine finger motion.<n>We show that Dexora outperforms competitive VLA baselines on both basic and dexterous benchmarks.
  arXiv  Detail & Related papers  (2026-05-18T17:50:32Z)
• RLDX-1 Technical Report [74.70437517338186]
  We introduce RLDX-1, a general-purpose robotic policy for dexterous manipulation built on the Multi-Stream Action Transformer (MSAT)<n>Through empirical evaluation, we show that RLDX-1 consistently outperforms recent frontier Vision-Language-Action models.
  arXiv  Detail & Related papers  (2026-05-05T01:40:15Z)
• Cross-Hand Latent Representation for Vision-Language-Action Models [49.32460749933983]
  Training reliable vision-language-action models for dexterous manipulation requires large-scale demonstrations across many robotic hands.<n>We introduce XL-VLA, a vision-language-action framework integrated with a unified latent action space shared across diverse dexterous hands.
  arXiv  Detail & Related papers  (2026-03-10T18:50:57Z)
• Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-of-Dexterous-Experts VLA [62.16042475700567]
  We introduce IMCopilot, a shared-autonomy assistant to simplify teleoperation data collection.<n>We present MoDE-VLA, an architecture that seamlessly integrates heterogeneous force and tactile modalities into a pretrained VLA backbone.<n>We validate our approach on four tasks of escalating complexity, demonstrating doubled success rate improvement over the baseline in dexterous contact-rich tasks.
  arXiv  Detail & Related papers  (2026-03-09T09:02:30Z)
• SOP: A Scalable Online Post-Training System for Vision-Language-Action Models [15.86316960521611]
  Vision-language-action (VLA) models achieve strong generalization through large-scale pre-training, but real-world deployment requires expert-level task proficiency in addition to broad generality.<n>Existing post-training approaches for VLA models are typically offline, single-robot, or task-specific.<n>We introduce a Scalable Online Post-training system that enables online, distributed, multi-task post-training of generalist VLA models directly in the physical world.
  arXiv  Detail & Related papers  (2026-01-06T14:25:11Z)
• METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action Model [36.82365894983052]
  A major bottleneck lies in the scarcity of large-scale, action-annotated data for dexterous skills.<n>We propose METIS, a vision-language-action model for dexterous manipulation pretrained on egocentric datasets.<n>Our method demonstrates exceptional dexterous manipulation capabilities, achieving highest average success rate in six real-world tasks.
  arXiv  Detail & Related papers  (2025-11-21T16:32:36Z)
• End-to-End Dexterous Arm-Hand VLA Policies via Shared Autonomy: VR Teleoperation Augmented by Autonomous Hand VLA Policy for Efficient Data Collection [10.217810309422232]
  We propose a framework that divides control between macro and micro motions.<n>A human operator guides the robot's arm pose through intuitive VR teleoperation.<n>An autonomous DexGrasp-VLA policy handles fine-grained hand control using real-time tactile and visual feedback.
  arXiv  Detail & Related papers  (2025-10-31T16:12:02Z)
• IntentionVLA: Generalizable and Efficient Embodied Intention Reasoning for Human-Robot Interaction [51.130510883952546]
  Vision-Language-Action (VLA) models leverage pretrained vision-language models (VLMs) to couple perception with robotic control.<n>We propose textbfIntentionVLA, a VLA framework with a curriculum training paradigm and an efficient inference mechanism.<n>Our proposed method first leverages carefully designed reasoning data that combine intention inference, spatial grounding, and compact embodied reasoning.
  arXiv  Detail & Related papers  (2025-10-09T04:49:46Z)
• 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)
• Human-assisted Robotic Policy Refinement via Action Preference Optimization [26.144183856600687]
  Action Preference Optimization (APO) is a method designed to refine Vision-Language-Action (VLA) models by human-assisted preference alignment.<n>To solve this, APO proposes an adaptive reweighting algorithm with binary desirability signals derived from interaction.<n>Experiments conducted in simulation and real-world scenarios prove superior generalization and robustness.
  arXiv  Detail & Related papers  (2025-06-08T13:14:18Z)
• DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulation [78.60543357822957]
  Dexterous manipulation with contact-rich interactions is crucial for advanced robotics.<n>We introduce DexHandDiff, an interaction-aware diffusion planning framework for adaptive dexterous manipulation.<n>Our framework achieves an average of 70.7% success rate on goal adaptive dexterous tasks, highlighting its robustness and flexibility in contact-rich manipulation.
  arXiv  Detail & Related papers  (2024-11-27T18:03:26Z)
• Robotic Control via Embodied Chain-of-Thought Reasoning [86.6680905262442]
  Key limitation of learned robot control policies is their inability to generalize outside their training data.<n>Recent works on vision-language-action models (VLAs) have shown that the use of large, internet pre-trained vision-language models can substantially improve their robustness and generalization ability.<n>We introduce Embodied Chain-of-Thought Reasoning (ECoT) for VLAs, in which we train VLAs to perform multiple steps of reasoning about plans, sub-tasks, motions, and visually grounded features before predicting the robot action.
  arXiv  Detail & Related papers  (2024-07-11T17:31:01Z)

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.