Summary

Currently employed at Red Brick University. Short biography for the left-hand sidebar

Education

• Ph.D., Faculty of Computer Science

  October 2020 - September 2023
  University of Stavanger & MSCA CLARIFY

  Stavanger, Norway

  • Thesis: Taking Computation to Data: Integrating Privacy-preserving AI techniques and Blockchain allowing secure analysis of sensitive data on premise
  • Advisors: Prof. Chunning Rong & Prof. Martin Gilje Jaatun
  • Academic Visits: Sept 2022–Oct 2022 with Prof. Hans-Arno Jacobsen, Technical University of Munich, Germany
  • Academic Visits: May 2022–July 2022 with Prof. Rafael Molina, University of Granada, Spain
  • Academic Visits: May 2021–July 2021 with Prof. Zhiming Zhao, University of Amsterdam, Netherlands
• M.S. in Computer Science

  September 2015 - October 2018
  RWTH Aachen University

  Aachen, Germany

  • Thesis: Unsupervised Learning of Neural Network Lexicon and Cross-lingual Word Embedding
  • Advisor: Prof. Hermann Ney
• B.S. in Automation

  September 2011 - June 2015
  Southeast University

  Nanjing, China

  • Thesis: Automatic Recognition of Road Markings Based on 3D Vision Transformation
  • Advisor: Prof. Shihua Li

Publications

• Sauce: Selective concept unlearning in vision-language models with sparse autoencoders

  2025
  IEEE/CVF International Conference on Computer Vision (ICCV 2025)

  A novel approach for selective concept unlearning in vision-language models using sparse autoencoders.

  View Publication
• Internal activation revision: Safeguarding vision language models without parameter update

  2025
  39th AAAI Conference on Artificial Intelligence (AAAI 2025)

  A method for safeguarding vision language models through internal activation revision without requiring parameter updates.

  View Publication
• Marco-Bench-MIF: A Multi-Modal Instruction Following Benchmark for Multimodal Large Language Models

  2025
  ACL 2025 Main Conference

  A comprehensive benchmark for evaluating multimodal instruction following capabilities of large language models.

  View Publication
• CaMMT: Cross-Modal Multi-Task Learning for Medical Image Analysis

  2025
  EMNLP 2025 Findings

  A novel approach for cross-modal multi-task learning in medical image analysis.

  View Publication
• CoQuIR: A Comprehensive Query-based Image Retrieval Dataset

  2025
  arXiv preprint

  A large-scale dataset for query-based image retrieval tasks.

  View Publication

Presentations

• Talk 1 on Relevant Topic in Your Field

  2012
  UC San Francisco, Department of Testing

  San Francisco, CA, USA
• Tutorial 1 on Relevant Topic in Your Field

  2013
  UC-Berkeley Institute for Testing Science

  Berkeley, CA, USA
• Talk 2 on Relevant Topic in Your Field

  2014
  London School of Testing

  London, UK
• Conference Proceeding talk 3 on Relevant Topic in Your Field

  2014
  Testing Institute of America 2014 Annual Conference

  Los Angeles, CA, USA

Teaching

• Teaching experience 1

  2014
  University 1, Department

  Role: Undergraduate course
• Teaching experience 2

  2015
  University 1, Department

  Role: Workshop

Portfolio

• Portfolio item number 1
  Portfolio

  Short description of portfolio item number 1
  

  View Project