GazeVLA: Learning Human Intention for Robotic Manipulation

• URL: http://arxiv.org/abs/2604.22615v2
• Date: Thu, 30 Apr 2026 12:27:46 GMT
• Title: GazeVLA: Learning Human Intention for Robotic Manipulation
• Abstract summary: Embodied foundation models have achieved significant breakthroughs in robotic manipulation, yet they still depend heavily on large-scale robot demonstrations.<n>We argue that the intention underlying human actions can serve as a powerful intermediate representation for bridging this gap.<n>We introduce a novel framework that explicitly learns and transfers human intention to facilitate robotic manipulation.
• Score: 22.106797717672293
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Embodied foundation models have achieved significant breakthroughs in robotic manipulation, yet they still depend heavily on large-scale robot demonstrations. Although recent works have explored leveraging human data to alleviate this dependency, effectively extracting transferable knowledge remains a significant challenge due to the inherent embodiment gap between human and robot. We argue that the intention underlying human actions can serve as a powerful intermediate representation for bridging this gap. In this paper, we introduce a novel framework that explicitly learns and transfers human intention to facilitate robotic manipulation. Specifically, we model intention through gaze, as it naturally precedes physical actions and serves as an observable proxy for human intent. Our model is first pretrained on a large-scale egocentric human dataset to capture human intention and its synergy with action, followed by finetuning on a small set of robot and human data. During inference, the model adopts a Chain-of-Thought reasoning paradigm, sequentially predicting intention before executing the action. Extensive evaluations in simulation and real-world settings, across long-horizon and fine-grained tasks, and under few-shot and robustness benchmarks, show that our method consistently outperforms strong baselines, generalizes better, and achieves state-of-the-art performance. Project page: https://gazevla.github.io .

Related papers

• EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data [114.89243396877453]
  We present EgoScale, a human to dexterous manipulation transfer framework built on large scale egocentric human data.<n>We introduce a simple two stage transfer recipe: large scale human pretraining followed by lightweight aligned human robot mid training.<n>Our final policy improves average success rate by 54% over a no pretraining baseline using a 22 DoF dexterous robotic hand.
  arXiv  Detail & Related papers  (2026-02-18T18:59:05Z)
• EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration [67.13034606664333]
  EgoHumanoid is the first framework to co-train a vision-language-action policy using egocentric human demonstrations.<n>A portable system for scalable human data collection is developed.
  arXiv  Detail & Related papers  (2026-02-10T18:59:03Z)
• MiVLA: Towards Generalizable Vision-Language-Action Model with Human-Robot Mutual Imitation Pre-training [102.850162490626]
  We propose MiVLA, a vision-language-action model empowered by human-robot mutual imitation pre-training.<n>We show that MiVLA achieves strong improved generalization capability, outperforming state-of-the-art VLAs.
  arXiv  Detail & Related papers  (2025-12-17T12:59:41Z)
• From Human Hands to Robot Arms: Manipulation Skills Transfer via Trajectory Alignment [36.08997778717271]
  Learning diverse manipulation skills for real-world robots is bottlenecked by reliance on costly and hard-to-scale teleoperated demonstrations.<n>We introduce Traj2Action, a novel framework that bridges this embodiment gap by using the 3D trajectory of the operational endpoint as a unified intermediate representation.<n>Our policy first learns to generate a coarse trajectory, which forms a high-level motion plan by leveraging both human and robot data.
  arXiv  Detail & Related papers  (2025-10-01T04:21:12Z)
• AR-VRM: Imitating Human Motions for Visual Robot Manipulation with Analogical Reasoning [5.371855090716962]
  Visual Robot Manipulation (VRM) aims to enable a robot to follow natural language instructions based on robot states and visual observations.<n>Existing approaches have employed vision-language pretraining with large-scale data.<n>We propose to learn from large-scale human action video datasets in an explicit way.
  arXiv  Detail & Related papers  (2025-08-11T05:09:58Z)
• DIRIGENt: End-To-End Robotic Imitation of Human Demonstrations Based on a Diffusion Model [16.26334759935617]
  We introduce DIRIGENt, a novel end-to-end diffusion approach to generate joint values from observing human demonstrations.<n>We create a dataset in which humans imitate a robot and then use this collected data to train a diffusion model that enables a robot to imitate humans.
  arXiv  Detail & Related papers  (2025-01-28T09:05:03Z)
• Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation [16.809190349155525]
  We propose a novel adaptation paradigm that leverages readily available paired human-robot video data to bridge the domain gap.<n>Our method employs a human-robot contrastive alignment loss to align the semantics of human and robot videos, adapting pre-trained models to the robot domain in a parameter-efficient manner.
  arXiv  Detail & Related papers  (2024-06-20T11:57:46Z)
• Learning Human-to-Robot Handovers from Point Clouds [63.18127198174958]
  We propose the first framework to learn control policies for vision-based human-to-robot handovers. We show significant performance gains over baselines on a simulation benchmark, sim-to-sim transfer and sim-to-real transfer.
  arXiv  Detail & Related papers  (2023-03-30T17:58:36Z)
• Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning [54.636562516974884]
  In imitation and reinforcement learning, the cost of human supervision limits the amount of data that robots can be trained on. In this work, we propose MEDAL++, a novel design for self-improving robotic systems. The robot autonomously practices the task by learning to both do and undo the task, simultaneously inferring the reward function from the demonstrations.
  arXiv  Detail & Related papers  (2023-03-02T18:51:38Z)
• HERD: Continuous Human-to-Robot Evolution for Learning from Human Demonstration [57.045140028275036]
  We show that manipulation skills can be transferred from a human to a robot through the use of micro-evolutionary reinforcement learning. We propose an algorithm for multi-dimensional evolution path searching that allows joint optimization of both the robot evolution path and the policy.
  arXiv  Detail & Related papers  (2022-12-08T15:56:13Z)
• Human Grasp Classification for Reactive Human-to-Robot Handovers [50.91803283297065]
  We propose an approach for human-to-robot handovers in which the robot meets the human halfway. We collect a human grasp dataset which covers typical ways of holding objects with various hand shapes and poses. We present a planning and execution approach that takes the object from the human hand according to the detected grasp and hand position.
  arXiv  Detail & Related papers  (2020-03-12T19:58:03Z)

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.