Shihan Wu (吴世涵)

MS Student, School of Computer Science and Engineering, University of Electronic science and technology of China (UESTC)

github
googleScholar
dblp

GitHub User's stars GitHub User's followers

Introduction

Computer Science Master student at University of Electronic Science and Technology of China (UESTC) (GPA Ranking: Top 1.3%), specializing in:

  • High-efficiency transfer learning for Vision-Language Models (VLMs)
  • Training and test-time adaptation for Vision-Language-Action Models (VLAs)

Published 2 CVPR (CCF-A) papers as first/co-first author. Awarded National Scholarship and Outstanding Graduate honors.

News

[2025.5.20] 🔥 Our paper "InSpire: Vision-Language-Action Models with Intrinsic Spatial Reasoning" is available!

[2025.5.19] 🔥 Our paper "Policy Contrastive Decoding for Robotic Foundation Models" is available!

Education & Experiences

→ Full list

Master student at University of Electronic Science and Technology of China (UESTC), 2023 - Present

Bachelor student at University of Electronic Science and Technology of China (UESTC), 2019 - 2023

Publications

→ Full list

Note: (*indicates equal contribution)

Policy Contrastive Decoding for Robotic Foundation Models

Shihan Wu*, Ji Zhang*, Xu Luo, Junlin Xie, Jingkuan Song, Heng Tao Shen, Lianli Gao

Robotics · Vision-Language-Action Models · Contrastive Decoding

2025.5

[Project Page] [PDF] [arXiv] [Code]

GitHub Repo stars

InSpire: Vision-Language-Action Models with Intrinsic Spatial Reasoning

Ji Zhang*, Shihan Wu*, Xu Luo, Hao Wu, Lianli Gao, Heng Tao Shen, Jingkuan Song

Robotics · Vision-Language-Action Models · Spurious Correlation

2025.5

[Project Page] [PDF] [arXiv] [Code]

GitHub Repo stars

[CVPR 2025] Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves

Shihan Wu, Ji Zhang, Pengpeng Zeng, Lianli Gao, Jingkuan Song, Heng Tao Shen

Vision-language Models · Transfer Learning · Efficiency

2024.12

[PDF] [arXiv] [Code]

GitHub Repo stars

Rethinking Conditional Prompt Tuning for Vision-Language Models

Ji Zhang, Shihan Wu, Pengpeng Zeng, Lianli Gao, Jingkuan Song, Heng Tao Shen

Vision-language Models · Transfer Learning · Prompt Tuning

2024.8

[Code]

GitHub Repo stars

[CVPR 2024] DePT: Decoupled Prompt Tuning

Ji Zhang*, Shihan Wu*, Lianli Gao, Heng Tao Shen, Jingkuan Song

Vision-language Models · Transfer Learning · Prompt Tuning

2023.9

[PDF] [arXiv] [Code]

GitHub Repo stars

Awards & Honors

→ Full list

Outstanding Graduate Student, University of Electronic Science and Technology of China (UESTC), 2025

National Scholarship, Ministry of Education of the People's Republic of China, 2024

Outstanding Graduate, University of Electronic Science and Technology of China (UESTC), 2023