Applications
HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System
arXiv:2604.14125v1 Announce Type: new 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
arXiv:2604.14125v1 Announce Type: new 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.
Related
- HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models
- HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation
- Robotic Manipulation is Vision-to-Geometry Mapping (f(v) rightarrow G): Vision-Geometry Backbones over Language and Video Models
- LARY: A Latent Action Representation Yielding Benchmark for Generalizable Vision-to-Action Alignment
- UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Models
Source: arXiv cs.CV | 2026-04-16