JH

Jingyang He

cs.ROcs.AI

On Valency

published · living versions

W_p6ssubkq·v1 · currentpublished

HAF-VLA: Hierarchical Action Flow Framework for Humanoid Vision-Language-Action Control

with Langzhe Gu, Chengkai Hou, Meng Li, Xinhua Wang +10

1 version

Preprints & journals

6 papers in the corpus · 2024–2026

HAF-VLA: Hierarchical Action Flow Framework for Humanoid Vision-Language-Action Control2610.26584v1 · Langzhe Gu, Chengkai Hou, Meng Li et al.2026 · 0 citationsarXivon Valency

HAF: Adapting Generalist VLAs to Humanoid Whole-Body Loco-manipulation via Hierarchical Action Flow and Spectral Latent RL2608.16837v1 · Langzhe Gu, Chengkai Hou, Meng Li et al.2026 · 0 citationsarXiv

Demo-JEPA: Joint-Embedding Predictive Architecture for One-shot Cross-Embodiment Imitation2605.20811v1 · Jingyang He, Guangrun Li, Jieyu Zhang et al.2026 · 0 citationsarXiv

VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models2605.10485v1 · Hao Wang, Xiaobao Wei, Jingyang He et al.2026 · 0 citationsarXiv

RoboMIND 2.0: A Multimodal, Bimanual Mobile Manipulation Dataset for Generalizable Embodied Intelligence2512.24653v3 · Chengkai Hou, Kun Wu, Jiaming Liu et al.2025 · 0 citationsarXiv

RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation2412.13877v3 · Kun Wu, Chengkai Hou, Jiaming Liu et al.2024 · 22 citationsarXiv

Career total: 6 works. 6 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.