Saved in:
Bibliographic Details
Main Authors: Wulff, Theodor, Tavella, Federico, Maharjan, Rahul Singh, Adikari, Manith, Cangelosi, Angelo
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.05614
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915920357621760
author Wulff, Theodor
Tavella, Federico
Maharjan, Rahul Singh
Adikari, Manith
Cangelosi, Angelo
author_facet Wulff, Theodor
Tavella, Federico
Maharjan, Rahul Singh
Adikari, Manith
Cangelosi, Angelo
contents Achieving robot transparency is a critical step toward effective human-robot collaboration. To be transparent, a robot's natural language communication must be consistent with its actions and explicitly grounded in the task and environment. Existing hierarchical Vision-Language-Action (VLA) models can generate language (e.g., through chain-of-thought) and low-level actions. However, current work does not consider explicit alignment between these modalities during training. To address this crucial gap, we propose a novel training framework that explicitly grounds hierarchical VLA sub-task descriptions with respect to the visual observation and action space. Our framework uses a contrastive model to assess the alignment between generated language and corresponding action trajectories. This contrastive model enables direct ranking of different language-trajectory pairs based on their alignment, allowing us to refine the grounding of our hierarchical VLA through offline preference learning. We apply our framework to the LanguageTable dataset, a benchmark dataset of human language-annotated trajectories, and provide critical insights into multimodal grounding representations, all while establishing a strong baseline that achieves performance comparable to fully supervised fine-tuning and minimizing the need for costly data annotations.
format Preprint
id arxiv_https___arxiv_org_abs_2604_05614
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Grounding Hierarchical Vision-Language-Action Models Through Explicit Language-Action Alignment
Wulff, Theodor
Tavella, Federico
Maharjan, Rahul Singh
Adikari, Manith
Cangelosi, Angelo
Robotics
Achieving robot transparency is a critical step toward effective human-robot collaboration. To be transparent, a robot's natural language communication must be consistent with its actions and explicitly grounded in the task and environment. Existing hierarchical Vision-Language-Action (VLA) models can generate language (e.g., through chain-of-thought) and low-level actions. However, current work does not consider explicit alignment between these modalities during training. To address this crucial gap, we propose a novel training framework that explicitly grounds hierarchical VLA sub-task descriptions with respect to the visual observation and action space. Our framework uses a contrastive model to assess the alignment between generated language and corresponding action trajectories. This contrastive model enables direct ranking of different language-trajectory pairs based on their alignment, allowing us to refine the grounding of our hierarchical VLA through offline preference learning. We apply our framework to the LanguageTable dataset, a benchmark dataset of human language-annotated trajectories, and provide critical insights into multimodal grounding representations, all while establishing a strong baseline that achieves performance comparable to fully supervised fine-tuning and minimizing the need for costly data annotations.
title Grounding Hierarchical Vision-Language-Action Models Through Explicit Language-Action Alignment
topic Robotics
url https://arxiv.org/abs/2604.05614