Kani: A Lightweight and Highly Hackable Framework for Building Language Model Applications
Andrew Zhu*, Liam Dugan*, Alyssa Hwang, and Chris Callison-Burch
CV
For those who prefer, here is my CV in PDF form
Education
- Ph.D Computer Science, University of Pennsylvania, 2027 (expected)
- M.S.E. Robotics, University of Pennsylvania, 2020
- B.S.E. Computer Engineering, University of Pennsylvania, 2020
Work experience
- Summer 2022: Research Intern, Roblox
- Summer 2021: Visiting Research Scholar, John’s Hopkins University
- Summer 2019: Software Engineering Intern, NVIDIA Corporation
- Summer 2018: Software Engineering Intern, Robotic Research
Technical Skills
- Natural Languages:
- English (native), Japanese (business fluent), Korean (elementary)
- Programming Languages:
- Python, C/C++, Java, bash, CUDA, MATLAB, R, JavaScript, HTML/CSS
- ML Frameworks/Libraries:
- PyTorch, Numpy, Pandas, Huggingface, Fairseq, Tensorflow, OpenCV
Publications
Enhancing Human Summaries for Question-Answer Generation in Education
Hannah Gonzalez, Liam Dugan, Eleni Miltsakaki, Zhiqi Cui, Jiaxuan Ren, Bryan Li, Shriyash Upadhyay, Etan Ginsberg, and Chris Callison-Burch
Learning When to Speak: Latency and Quality Trade-offs for Simultaneous Speech-to-Speech Translation with Offline Models
Liam Dugan, Anshul Wadhawan, Kyle Spence, Chris Callison-Burch, Morgan McGuire, and Victor Zordan
Exploring the Curious Case of Code Prompts
Li Zhang*, Liam Dugan*, Hainiu Xu*, and Chris Callison-Burch
Real or Fake Text? Investigating Human Ability to Detect Boundaries Between Human-Written and Machine-Generated Text
Liam Dugan*, Daphne Ippolito*, Arun Kirubarajan, Sherry Shi, and Chris Callison-Burch
The Case for a Single Model that can both Generate Continuations and Fill-in-the-Blank
Daphne Ippolito, Liam Dugan, Emily Reif, Ann Yuan, Andy Coenen, and Chris Callison-Burch
Beyond the Imitation Game: Quantifying and Extrapolating the Capabilities of Language Models
Aarohi Srivastava, Abhinav Rastogi, and (440 others)
A Feasibility Study of Answer-Agnostic Question Generation for Education
Liam Dugan, Eleni Miltsakaki, Shriyash Upadhyay, Etan Ginsberg, Hannah Gonzalez, DaHyeon Choi, Chuning Yuan, and Chris Callison-Burch
RoFT: A Tool for Evaluating Human Detection of Machine-Generated Text
Liam Dugan, Daphne Ippolito*, Arun Kirubarajan*, and Chris Callison-Burch
Cloud Chaser: Real Time Deep Learning Computer Vision on Low Computing Power Devices
Zhengyi Luo, Austin Small, Liam Dugan, and Stephen Lane
Talks
Exploring the Curious Case of Code Prompts
Conference Talk at NLRSE Workshop @ ACL 2023, Toronto, Canada
Should we still use Text for Speech-to-Speech Translation? Promise meets Practice
Invited Talk at John's Hopkins HLTCOE Seminar, Baltimore, MD
Detecting Generated Text from ChatGPT (and other LLMs)
Invited Panel Talk at Penn Critical Writing Seminar Panel, Virtual
Real or Fake Text?: Investigating Human Ability to Detect Boundaries Between Human-Written and Machine-Generated Text
Conference Talk at AAAI 2023, Washington, DC
Introduction to Machine Learning and AI Research
Invited Talk at St. Joseph's Prep High School, Philadelphia, PA
Learning Formality from Japanese-English Parallel Corpora
Thesis Presentation at University of Pennsylvania, Philadelphia, PA
Scene++ VR: Senior Design Presentation
Senior Design Presentation at University of Pennsylvania, Philadelphia, PA
Cloud Chaser: PennApps XVII Presentation
Hackathon Presentation at University of Pennsylvania, Philadelphia, PA
Todd The Inter-Dimensional Robot: PennApps XVI Presentation
Hackathon Presentation at University of Pennsylvania, Philadelphia, PA
Teaching
Fellowships and Grants
- (August 2022) Roblox Research Grant - $100,000
- (October 2021) Google Cloud Platform Research Grant - $5,500
- (October 2018) Foreign Language and Area Studies Undergraduate Fellowship (East Asia) - $15,000