πŸ‘€ About Me

Hi! I’m a last-year undergraduate student from School of Mathematics, Tianjin University. Currently, I am an research intern at RZ-Lab, Purdue University, advised by Dr. Ruqi Zhang. Meanwhile, I’m also a research assistant in the MLDM Lab Multimodal Vision Processing (MVP) Group, advised by Dr. Bing Cao and Prof. Qinghua Hu. I am interested in building reliable machine learning algorithms/frameworks in the real world, especially on the alignment of Large Foundation Models (LLMs, VLMs) and the generalization of multimodal learning algorithms.

πŸ’– Research Interests

  • Multimodal Learning: Multimodal Fusion, Imbalanced Multimodal Learning.
  • Alignment of Foundation Models: LLMs, VLMs.
  • Trustworthy AI: Safety, Uncertainty, etc.

I'm finding 25 Fall PhD opportunities! You can find my CV here. If you share the same research interests with me, welcome to add my Wechat

πŸ”₯ News

  • [Oct. 2024]: Β πŸŽ‰πŸŽ‰πŸŽ‰ Our Paper about Inference Time Alignment of LVLMs is preprinted now. You can use our ETA to safeguard your Large Vision Language Models (LVLMs)!
  • [Sep. 2024]: Β πŸŽ‰πŸŽ‰πŸŽ‰ Yi serves as Reviewer of ICLR 2025!
  • [Sep. 2024]: Β πŸŽ‰πŸŽ‰πŸŽ‰ Our paper about Dynamic Image Fusion without additional training is accepted to NeurIPS 2024! Congratulations to all Collaborators!
  • [Jul. 2024]: Β πŸŽ‰πŸŽ‰πŸŽ‰ Yi will make a poster presentation at Tue 23 Jul 1:30 p.m. β€” 3 p.m. on ICML Hall C 4-9 #2817, Vienna, Austria!
  • [May. 2024]: Β πŸŽ‰πŸŽ‰πŸŽ‰ Our paper about Multimodal Fusion is accepted to ICML 2024!

πŸ“ Publications & Preprints

* indicates author with equal contribution.

arXiv 2024
sym

ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time

Yi Ding, Bolian Li, Ruqi Zhang

TL;DR: Establishing multimodal safety mechanism for VLMs and enhancing harmlessness and helpfulness of responses without additional training.

Priprint.

[PDF] [Project Page] [CODE]

NeurIPS 2024
sym

Test-Time Dynamic Image Fusion

Bing Cao, Yinan Xia*, Yi Ding*, Changqing Zhang, Qinghua Hu

TL;DR: Improving quality of fused images of almost every backbones without additional training via setting dynamic weight in test-time.

Neural Information Processing Systems (NeurIPS), 2024

[PDF] [CODE]

ICML 2024
sym

Predictive Dynamic Fusion

Bing Cao, Yinan Xia*, Yi Ding*, Changqing Zhang, Qinghua Hu

TL;DR: The key to dynamic fusion lies in the correlation between the weights and the loss, providing generalization theory for decision-level fusion.

International Conference on Machine Learning (ICML), 2024

[PDF] [CITE] [CODE]

πŸ“– Educations

  • 2021.08 - Present, B.S., School of Mathematics, Tianjin University
  • 2024.05 - Present, Intern, Department of Computer Science, Purdue University