Yifan Wu

Hi there! I'm a Research Scientist at Meta GenAI, working on multimodal foundation models for Meta AI.

I recently earned my PhD from the University of Pennsylvania, where I was affiliated with UPenn GRASP Lab and Penn Image Computing and Science Laboratory. I was grateful to be advised by Prof. James C. Gee, and closely worked with Prof. Jianbo Shi and Prof. Mark Yatskar.

Email: yfwu@seas.upenn.edu  /  Google Scholar  /  Linkedin

We demonstrated how to encode the expertise of specialized clinicians into AI to build an interpretable machine learning model that produces outputs understandable by humans.

We found that GPT-4V can benefit significantly from the Chain-of-Thought prompt. We present the "Description then Decision" strategy, which improves Winoground task performance by 50%.

We established dense correspondence in multi-view angiography by formulating it as a query matching problem and extending point matching to curve matching for enhanced topological awareness.

We model each voxel as a moving particle and consider the set of all voxels in a 3D image as a high-dimensional dynamical system whose trajectory determines the targeted deformation field.

Formulated the radiologic ILD findings identification as a multi-class classification problem given the raw thoracic CT dataset.

We propose to use constrained inpainting methods to recover usability of corrupted images, which are masked for privacy protection but complete images are required for further algorithm development.

This paper presents a method to generate a volumetric phantom with internal anatomical structures from the patient?s skin surface geometry.

Defined the face-identification task by establishing an effective de-identification measurement: achieve privacy protection simultaneously preserving data utility. Proposed an end-to-end trainable framework to synthesize de-identified facial images.

Website template from Jon Barron.