Zuhao Ge — accepted AI-conference papers

2026

GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization

Xiaosong Jia, Bowen Yang, Zuhao Ge, Xian Nie, Yuchen Zhou, Cunxin Fan +14

RSS 2026poster

Vision-Language-Action (VLA) models aim for general robot learning by aligning action as a modality within powerful Vision-Language Models (VLM). Existing VLAs rely on end-to-end supervision to implicitly enable the action decoding process to learn task-relevant features. However, without explicit g…

Cited by 0 Source ↗Scholar ↗

2023

Explicit and Implicit Knowledge Distillation via Unlabeled Data

Yuzheng Wang, Zuhao Ge, Zhaoyu Chen, Xian Liu, Chuangjia Ma, Yunquan Sun +1

ICASSP 2023accepted

Data-free knowledge distillation is a challenging model lightweight task for scenarios in which the original dataset is not available. Previous methods require a lot of extra computational costs to update one or more generators and their naive imitate-learning lead to lower distillation efficiency.…

Cited by 0 Source ↗Scholar ↗