I am a third-year undergraduate student at Ohio State University with a strong research focus in Computer Vision, Vision-language Models, and Multimodalities. My academic journey includes active participation in North Carolina State University’s GEARS research, where I delved into data mining and applied machine learning and deep learning algorithms. Additionally, Before transferring to OSU, I had research experience at the Computer Vision Laboratory of Xi’an Jiaotong-Liverpool University, further refining my expertise in the field.

I currently have a research internship at Prof.Chaowei Xiao’s Lab at University of Wisconsin-Madison.

In pursuit of academic excellence, I have served as a research assistant at OSU NLP Group and ICICLE Institute under the mentorship of Prof.Yu Su. This valuable experience has significantly contributed to my understanding of natural language processing and multi-modalities. My current research interests mainly focus on the safety and trustworthiness of AI including large language models and multi-modality ones.

As I prepare to advance my academic career, I am gearing up to apply for a Ph.D. program in the fall of 2025. My multifaceted research background and hands-on experience in various research environments have equipped me with a robust skill set and a deep passion for advancing the frontiers of knowledge in the realm of computer science and artificial intelligence. I am enthusiastic about the prospect of contributing to cutting-edge research in my future academic endeavors.

My CV is here: Eddy’s Curriculum Vitae.

📰 News

  • 2024.07.16🎉, Our paper Bringing Back the Context: Camera Trap Species Identification as Link Prediction on Multimodal Knowledge Graphs has been accepted by CIKM’2024
  • 2024.07.09🎉, Our paper JailBreakV-28K: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks has been accepted by COLM’2024

🎓 Education

  • 2022.09 - 2025.06, B.A. in Computer and Information Science, Art and Science College, The Ohio State University (Dean List of Art and Science College in 22 Fall and 24 SP)
  • 2020.09 - 2022.04, B.SC. in Information and Computing Science, School of Advanced Technology, Xi’an Jiaotong Liverpool University (First Class)

📝 Pre-print

Arxiv
icon

Siyuan Ma*, Weidi Luo*, Yu Wang, Xiaogeng Liu, Muhao Chen, Bo Li, Chaowei Xiao, Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character, [paper] [code].

Arxiv
icon

Weidi Luo*, He Cao*, Yu Wang, Zijing Liu, Aidan Wong, Bin Feng, Yuan Yao, Yu Li, Guide for Defense (G4D): Dynamic Guidance for Robust and Balanced Defense in Large Language Models, [paper] [code].

Arxiv
icon

Jiongxiao Wang, Peiran Li, Siyuan Ma, Peiran Wang, Xiaogeng Liu, Jiashuo Sun, Yiming Liang, Tian Xia, Yu Wang, Weidi Luo, Chaowei Xiao, Prompt Injection Benchmark for Foundation Model Integrated Systems.

📸 Publication

COLM'2024
sym

Weidi Luo*, Siyuan Ma*, Xiaogeng Liu*, Xiaoyu Guo, Chaowei Xiao, JailBreakV-28K: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks, [paper] [Project Page] [code].

CIKM'2024
icon

Vardaan Pahuja, Weidi Luo, Yu Gu, Cheng-Hao Tu, Hong-You Chen, Tanya Berger-Wolf, Charles Stewart, Song Gao, Wei-Lun Chao, Yu Su, Bringing Back the Context: Camera Trap Species Identification as Link Prediction on Multimodal Knowledge Graphs, [Paper] [Project Page] [Code].

🖼 Poster

GEARS'2022
icon

Danying Xu; Weidi Luo; Yuxin Sun, Analysis and Prediction Models For NBA Games, [report].

🏅 Award

Award
icon

Weidi Luo, Bin Hu, Classification models for HEp-2 cell dataset

🏛️ Conference

  • 2024.10, CONFERENCE ON LANGUAGE MODELING(COLM)’2024, Philadelphia, PA, United State

💻 Internship

  • 2023.12 - now, Chaowei Xiao’s Lab, Madison, Wisconsin, United States
  • 2022.08 - 2023.12, ICICLE Institute|OSU NLP Group, Columbus, Ohio, United State
  • 2021.12 - 2022.05, Computer Vision Lab at Xi’an Jiaotong Liverpool University , Suzhou, Jiangsu, China