MY

Maoqing Yao

cs.ROcs.CVcs.AIcs.LG

On Valency

published · living versions

W_d5eabf98·v1 · currentpublished

Rollback: Experience Backtracking in World Models for Policy Improvement

with Jiayi Luo, Yang Zhang, Liliang Chen, Nan Wang +11

1 version

W_au6x24qc·v1published

Ego-CEVR: Learning Cross-Embodiment Visual Representations from Human Egocentric Videos

Preprints & journals

7 papers in the corpus · 2025–2026

MEgoVista: Multi-view Ego-aware Motion Estimation for Metric 4D Hands and Head in the Wild2609.16684v3 · Jiangong Xiao, Chao Ma, Zhihao Zhang et al.2026 · 0 citationsarXiv

CIDER: Continual Interactive Distillation for Embodied Reinforcement Learning2608.21899v1 · Houlin Li, Minghui Xu, Guo Xu et al.2026 · 0 citationsarXiv

Genie Sim PanoWorld: An Infinite Indoor 3D World Generation Pipeline via Panoramic Scene Modeling and Simulation2607.26646v1 · Yongxin Su, Linjie Hou, Feng Wang et al.2026 · 0 citationsarXiv

VINE: Taming Generative Control Policies for Reinforcement Learning2607.10369v1 · Rushuai Yang, Zhuo Han, Houlin Li et al.2026 · 0 citationsarXiv

ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training2602.12691v3 · Rushuai Yang, Hecheng Wang, Zhichao Wu et al.2026 · 0 citationsarXiv

ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models2601.11404v2 · Linqing Zhong, Yi Liu, Yifei Wei et al.2026 · 0 citationsarXiv

EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation2501.01895v3 · Siyuan Huang, Liliang Chen, Pengfei Zhou et al.2025 · 0 citationsarXiv

Career total: 11 works. 7 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.