Mingzhe Wang

I am a Ph.D. student in the Department of Computer Science at Princeton University, where I work with Prof. Jia Deng in the Princeton Vision & Learning Lab.

I received my master’s degree from the University of Michigan, working together with Prof. Jia Deng and Prof. Rada Mihalcea. I received my bachelor’s degree from Peking University, working with Prof. Ming Zhang.

Email  /  Google Scholar  /  Github

I am interested in automated reasoning, machine learning, and artificial intelligence in general. My current research focuses on building machine learning techniques to advance automated theorem proving. Prior to that, I worked on joint language and vision recognition and graph representation learning.

We present MetaGen, a neural theorem generator to generate synthetic theorems for the purpose of training the neural theorem prover.

We introduce a unified framework to generate surrogate losses for training deep networks with gradient descent, reducing the amount of manual design of task-specific surrogate losses.

We propose a new model for speaker naming in movies that leverages visual, textual, and acoustic modalities in an unified optimization framework.

We propose a graph embedding-based approach to the problem of premise selection: selecting mathematical statements relevant for proving a given conjecture.

We propose a structured matching of phrases and regions that encourages the semantic relations between phrases to agree with the visual relations between regions.

We propose a novel network embedding method called the "LINE," which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted.

Reviewer: CVPR, ICCV, ECCV, NeurIPS, ICML