Mingkai Deng
mingkaid [at] cs [dot] cmu [dot] edu

I am a first-year PhD student at the Language Technologies Institute at Carnegie Mellon University, working with Prof. Eric P. Xing. I also work very closely with Prof. Zhiting Hu. My current research interests include visual reasoning and natural language generation.

I did my MS at CMU's Machine Learning Department. Prior to that, I worked as a data scientist in the industry after interning at Baidu Research, supervised by Prof. Hui Xiong. I did my undergrad at Columbia University, where I double-majored in Mathematics-Statistics and Computer Science.

CV  /  LinkedIn  /  Twitter  /  GitHub

• 2022-10 Our paper "RLPrompt: Optimizing Discrete Text Prompts With Reinforcement Learning" accepted by EMNLP 2022
• 2021-10 Post about our EMNLP 2021 paper is published at ML@CMU Blog
• 2021-09 Our paper "Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation" accepted by EMNLP 2021
• 2020-08 Concluded my wonderful time at Weber Shandwick
• 2019-06 Started internship with Prof. Hui Xiong at Baidu Research
• 2018-11 Our project "Data-Driven Analysis and Prediction of Gentrification in New York City" won Best Insights Award at Columbia ASA DataFest

An efficient and flexible framework for using RL to optimize prompts of discrete text that enable pre-trained LMs (e.g., BERT, GPT-2) to perform diverse NLP tasks. Experiments on few-shot classification and unsupervised text style transfer show superior performance to a wide range of existing methods.

A general framework that helps solve the difficulty of evaluating natural language generation (NLG) with a single unified operation. Inspired evaluation metrics improve over SOTA metrics for diverse NLG tasks. Our metrics are available as library on PyPI and GitHub.

Combine structured point-of-interest (POI, e.g., parking lots and buildings) data with unstructured satellite image data to automatically identify and draw the boundaries of urban areas-of-interest (e.g., residential areas and campuses).

Formulate the Transformer model as an ordinary differential equation (ODE) and perform forward-backward operations using an ODE solver. The resulting continuous-depth model has fewer parameters, converges faster, and shows promising performance in empirical experiments.

A data-driven narrative of NYC gentrification patterns over time and their second-order impact on the city's inhabitants. Construct significant leading predictors using resources from NYC OpenData.

The source code of this website is adapted from here