author

Hi there! I am Baichuan Li

Master of Computer Science
@ University of Michigan

Find out more about me

Skills

Click the images below to find out more

Linux

CUDA

Python

C / C++

Docker

Kubernetes

Flask

Unity

Dafny Formal Verification

Education

University of Michigan - Ann Arbor

Ph.D. of Computer Science

August 2025 - Now

University of Michigan - Ann Arbor

Master of Computer Science

August 2023 - April 2025

University of Michigan - Ann Arbor

Bachelor of Computer Science

August 2021 - April 2023

Shanghai Jiaotong University

Bachelor of Electrical & Computer Engineering

September 2019 - June 2021

Publications

Research Image

MTP: A Meaning-Typed Language Abstraction for AI-Integrated Programming

Software development is shifting from traditional programming to AI-integrated applications that leverage generative AI and large language models (LLMs) during runtime. However, integrating LLMs remains complex, requiring developers to manually craft prompts and process outputs. Existing tools attempt to assist with prompt engineering, but often introduce additional complexity. This paper presents Meaning-Typed Programming (MTP), a novel paradigm that abstracts LLM integration through intuitive language-level constructs. By leveraging the inherent semantic richness of code, MTP automates prompt generation and response handling without additional developer effort. We introduce the (1) by operator for seamless LLM invocation, (2) MT-IR, a meaning-based intermediate representation for semantic extraction, and (3) MT-Runtime, an automated system for managing LLM interactions. We implement MTP in Jac, a programming language that supersets Python, and find that MTP significantly reduces coding complexity while maintaining accuracy and efficiency. MTP significantly reduces development complexity, lines of code modifications needed, and costs while improving run-time performance and maintaining or exceeding the accuracy of existing approaches. Our user study shows that developers using MTP completed tasks 3.2x faster with 45% fewer lines of code compared to existing frameworks. Moreover, MTP demonstrates resilience even when up to 50% of naming conventions are degraded, demonstrating robustness to suboptimal code. MTP is developed as part of the Jaseci open-source project, and is available under the module by LLM.

Code