Pith. sign in

Gaze2Act: Gaze-Conditioned Vision-Language-Action Policies for Interactive Robot Manipulation

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it
abstract

Vision-Language-Action (VLA) models have recently shown strong potential for robot learning by following language instructions. However, in practice, language alone is often insufficient to precisely convey human intent. It is difficult to describe which exact object to interact with among similar candidates, where to act on the object, or how the target may change during execution. To address this limitation, we propose Gaze2Act, a novel VLA framework that leverages human gaze as a dynamic and intuitive intent signal for complex interactive manipulation. Gaze2Act first bridges the ego-exo view gap by mapping first-person gaze into the robot's perspective through cross-view semantic matching, producing both an object mask and a gaze point for coarse-to-fine target specification. These cues are then integrated into the policy through perception-level prompting and action-level conditioning, allowing the robot to attend to relevant regions and execute precise interactions under dynamic intent. In a systematic evaluation across seven task categories and 16 real-robot tasks on a Unitree G1 humanoid, Gaze2Act achieves state-of-the-art performance in both intent accuracy and task success rate. It notably outperforms baselines in object disambiguation, fine-grained interaction, and dynamic intent steering. These results demonstrate that human gaze provides a natural, low-burden, and highly expressive modality for human-in-the-loop VLA control.

fields

cs.RO 2

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

LA4VLA: Learning to Act without Seeing via Language-Action Pretraining

cs.RO · 2026-06-25 · unverdicted · novelty 6.0 · 2 refs

LA4VLA creates a 33K language-action dataset from existing demos and shows that pretraining on language-action pairs before or alongside vision-language-action training boosts success rates in sim and real robot tasks.

GIVE: Grounding Human Gestures in Vision-Language-Action Models

cs.RO · 2026-06-11 · unverdicted · novelty 5.0

GIVE improves pre-trained VLA models for robotic tasks by incorporating gestures via visual skeleton overlays and semantic descriptions, yielding 40% higher object recognition accuracy and 80% higher task success in real-world HRI experiments.

citing papers explorer

Showing 2 of 2 citing papers.

  • LA4VLA: Learning to Act without Seeing via Language-Action Pretraining cs.RO · 2026-06-25 · unverdicted · none · ref 9 · 2 links · internal anchor

    LA4VLA creates a 33K language-action dataset from existing demos and shows that pretraining on language-action pairs before or alongside vision-language-action training boosts success rates in sim and real robot tasks.

  • GIVE: Grounding Human Gestures in Vision-Language-Action Models cs.RO · 2026-06-11 · unverdicted · none · ref 3 · internal anchor

    GIVE improves pre-trained VLA models for robotic tasks by incorporating gestures via visual skeleton overlays and semantic descriptions, yielding 40% higher object recognition accuracy and 80% higher task success in real-world HRI experiments.