Gaze-Regularized Vision-Language-Action Models for Robotic Manipulation

• URL: http://arxiv.org/abs/2603.23202v1
• Date: Tue, 24 Mar 2026 13:50:28 GMT
• Title: Gaze-Regularized Vision-Language-Action Models for Robotic Manipulation
• Abstract summary: We introduce a gaze-regularized training framework that aligns VLA models' internal attention with human visual patterns.<n>When integrated into existing VLA architectures, our approach yields 4-12% improvements across manipulation benchmarks.
• Score: 7.281396624646809
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite advances in Vision-Language-Action (VLA) models, robotic manipulation struggles with fine-grained tasks because current models lack mechanisms for active visual attention allocation. Human gaze naturally encodes intent, planning, and execution patterns -- offering a powerful supervisory signal for guiding robot perception. We introduce a gaze-regularized training framework that aligns VLA models' internal attention with human visual patterns without architectural modifications or inference-time overhead. Our method transforms temporally aggregated gaze heatmaps into patch-level distributions and regularizes the transformer's attention through KL divergence, creating an inductive bias toward task-relevant features while preserving deployment efficiency. When integrated into existing VLA architectures, our approach yields 4-12% improvements across manipulation benchmarks. The gaze-regularized models reach equivalent performance with fewer training steps and maintain robustness under lighting variations and sensor noise. Beyond performance metrics, the learned attention patterns produce interpretable visualizations that mirror human strategies, enhancing trust in robotic systems. Moreover, our framework requires no eye-tracking equipment and applies directly to existing datasets. These results demonstrate that human perceptual priors can significantly accelerate robot learning while improving both task performance and system interpretability.

Related papers

• Artificial Foveated Perception for Mitigating Shortcut Learning in Robotic Foundation Models [28.23835152537988]
  We propose Artificial Foveated Perception (AFP), a lightweight, policy-agnostic module for robotic foundation models.<n>AFP predicts task-conditioned masks over relevant objects, the robot, and other action-critical regions.<n>We show AFP reduces fine-tuning time, suppresses overfitting, and improves generalization under environmental perturbations.
  arXiv  Detail & Related papers  (2026-07-12T08:42:36Z)
• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination [55.982504915794514]
  We propose Self-Correcting VLA (SC-VLA), which achieve self-improvement by intrinsically guiding action refinement through sparse imagination.<n>SC-VLA achieve state-of-the-art performance, yielding the highest task throughput with 16% fewer steps and a 9% higher success rate than the best-performing baselines.
  arXiv  Detail & Related papers  (2026-02-25T06:58:06Z)
• 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)
• PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention [92.85371254435074]
  PosA-VLA framework anchors visual attention via pose-conditioned supervision, consistently guiding the model's perception toward task-relevant regions.<n>We show that our method executes embodied tasks with precise and time-efficient behavior across diverse robotic manipulation benchmarks.
  arXiv  Detail & Related papers  (2025-12-03T12:14:29Z)
• Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations [76.79742393097358]
  Vision-Language Action (VLAs) models promise to extend the remarkable success of vision-language models (VLMs) to robotics.<n>Existing fine-tuning methods lack specificity, adapting the same set of parameters regardless of a task's visual, linguistic, and physical characteristics.<n>Inspired by functional specificity in neuroscience, we hypothesize that it is more effective to finetune sparse model representations specific to a given task.
  arXiv  Detail & Related papers  (2025-11-27T18:50:21Z)
• Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey [13.43815806675263]
  Vision-Language-Action (VLA) models extend vision-language models to embodied control by mapping natural-language instructions and visual observations to robot actions.<n>Despite their capabilities, VLA systems face significant challenges due to their massive computational and memory demands.
  arXiv  Detail & Related papers  (2025-10-20T02:59:45Z)
• Mechanistic interpretability for steering vision-language-action models [0.23371356738437823]
  Vision-Language-Action (VLA) models are a promising path to realizing generalist embodied agents.<n>We introduce the first framework for interpreting and steering VLAs via their internal representations.<n>We introduce a general-purpose activation steering method that modulates behavior in real time, without fine-tuning, reward signals, or environment interaction.
  arXiv  Detail & Related papers  (2025-08-30T03:01:57Z)
• Look, Focus, Act: Efficient and Robust Robot Learning via Human Gaze and Foveated Vision Transformers [2.736848514829367]
  Human vision is a highly active process driven by gaze, which directs attention to task-relevant regions through foveation.<n>In this work, we explore how incorporating human-like active gaze into robotic policies can enhance efficiency and robustness.<n>We develop GIAVA, a robot vision system that emulates human head and neck movement, and gaze adjustment for foveated processing.
  arXiv  Detail & Related papers  (2025-07-21T17:44:10Z)
• ROSA: Harnessing Robot States for Vision-Language and Action Alignment [24.426285156386715]
  Vision-Language Models (VLMs) have made significant advance in end-to-end robotic control.<n>We propose a novel training paradigm, ROSA, which leverages robot state estimation to improve alignment between vision-language and action spaces.
  arXiv  Detail & Related papers  (2025-06-16T16:34:20Z)
• TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies [95.30717188630432]
  We introduce visual trace prompting to facilitate VLA models' spatial-temporal awareness for action prediction.<n>We develop a new TraceVLA model by finetuning OpenVLA on our own collected dataset of 150K robot manipulation trajectories.<n>We present a compact VLA model based on 4B Phi-3-Vision, pretrained on the Open-X-Embodiment and finetuned on our dataset.
  arXiv  Detail & Related papers  (2024-12-13T18:40:51Z)
• Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics [68.36528819227641]
  This paper systematically evaluates the robustness of Vision-Language-Action (VLA) models.<n>We introduce two untargeted attack objectives that leverage spatial foundations to destabilize robotic actions, and a targeted attack objective that manipulates the robotic trajectory.<n>We design an adversarial patch generation approach that places a small, colorful patch within the camera's view, effectively executing the attack in both digital and physical environments.
  arXiv  Detail & Related papers  (2024-11-18T01:52:20Z)

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.