HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System

TL;DR

HiVLA introduces a hierarchical framework that separates high-level planning from low-level control, enhancing robotic manipulation by preserving reasoning and improving fine-grained task execution.

Contribution

The paper presents HiVLA, a novel decoupled architecture combining a VLM-based planner with a flow-matching Diffusion Transformer for robust manipulation.

Findings

HiVLA outperforms state-of-the-art end-to-end models in simulation and real-world tasks.

It excels in long-horizon skill composition and manipulating small objects in cluttered scenes.

The architecture maintains zero-shot reasoning while allowing independent component improvements.

Abstract

While end-to-end Vision-Language-Action (VLA) models offer a promising paradigm for robotic manipulation, fine-tuning them on narrow control data often compromises the profound reasoning capabilities inherited from their base Vision-Language Models (VLMs). To resolve this fundamental trade-off, we propose HiVLA, a visual-grounded-centric hierarchical framework that explicitly decouples high-level semantic planning from low-level motor control. In high-level part, a VLM planner first performs task decomposition and visual grounding to generate structured plans, comprising a subtask instruction and a precise target bounding box. Then, to translate this plan into physical actions, we introduce a flow-matching Diffusion Transformer (DiT) action expert in low-level part equipped with a novel cascaded cross-attention mechanism. This design sequentially fuses global context, high-resolution object-centric crops and skill semantics, enabling the DiT to focus purely on robust execution. Our decoupled architecture preserves the VLM's zero-shot reasoning while allowing independent improvement of both components. Extensive experiments in simulation and the real world demonstrate that HiVLA significantly outperforms state-of-the-art end-to-end baselines, particularly excelling in long-horizon skill composition and the fine-grained manipulation of small objects in cluttered scenes.