Yuling (Daniel) Shi

Yuling (Daniel) Shi

About me

Bio

Hi, I am a forth year Ph.D. student in the LLM for Software Engineering Lab (LLMSE), affiliated with the School of Software at Shanghai Jiao Tong University in China. I’m grateful to be advised by Prof. Xiaodong Gu and Prof. Beijun Shen.

My main research interests are in the field of Natural Language Processing and Software Engineering. Some of my recent projects can be found in my Github homepage here. Feel free to contact me if you are interested in my work or have any questions.

We have multiple potential projects available with abundant computing resources! If you are interested in collaboration or internship (remote is also welcome), please feel free to contact me.

Preprints

SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution

Han Li†, Yuling Shi†, Shaoxin Lin, Xiaodong Gu, Heng Lian, Xin Wang, Yantao Jia, Tao Huang, Qianxiang Wang

TL;DR: A competitive multi-agent debate framework for software issue resolution.

📄 pdf 💻 code

† Equal contribution

SWE-Exp: Experience-Driven Software Issue Resolution

Silin Chen, Shaoxin Lin, Xiaodong Gu, Yuling Shi, Heng Lian, Longfei Yun, Dong Chen, Weiguo Sun, Lin Cao, Qianxiang Wang

TL;DR: An experience-driven approach for software issue resolution.

📄 pdf 💻 code

EVOC2RUST: A Skeleton-guided Framework for Project-Level C-to-Rust Translation

Chaofan Wang, Tingrui Yu, Jie Wang, Dong Chen, Wenrui Zhang, Yuling Shi, Xiaodong Gu, Beijun Shen

TL;DR: An automated framework for converting entire C projects to equivalent Rust ones using skeleton-guided translation strategy.

📄 pdf

Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal

Wenhao Zeng, Yaoning Wang, Chao Hu, Yuling Shi, Chengcheng Wan, Hongyu Zhang, Xiaodong Gu

TL;DR: A novel coarse-to-fine framework for Chain-of-Thought compression in code reasoning tasks.

📄 pdf 💻 code

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging

Yuling Shi, Songsong Wang, Chengcheng Wan, Min Wang, Xiaodong Gu

TL;DR: A multi-level LLM debugger.

📄 pdf 💻 code

Publications

LastingBench: Defend Benchmarks Against Knowledge Leakage

Yixiong Fang, Tianran Sun, Yuling Shi, Min Wang, Xiaodong Gu

EMNLP 2025 Findings

TL;DR: A framework to continuously reinforce and safeguard existing benchmarks against knowledge leakage.

📄 pdf 💻 code

AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation

Yixiong Fang, Tianran Sun, Yuling Shi, Xiaodong Gu

ACL 2025 Workshop

TL;DR: An attention-guided context compression method for long context scenarios.

📄 pdf

Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human Programmers

Yuling Shi, Hongyu Zhang, Chengcheng Wan, Xiaodong Gu

ICSE 2025

TL;DR: A zero-shot LLM-generated code detector.

📄 pdf 💻 code 📊 slides

A Morley-Wang-Xu element method for a fourth order elliptic singular perturbation problem

Xuehai Huang, Yuling Shi and Wenqing Wang

Journal of Scientific Computing (Q1), 2021

TL;DR: A FEM solver for PDEs.

📄 pdf 💻 code

Experiences

  • Research Intern at Microsoft, 2023

    • I’m grateful to be advised by Dr. Yufan Huang and Dr. Maoquan Wang to work on analyzing neural representations of code. And some of my work contributed to the following paper on EMNLP 2023. [pdf]

Teaching

  • Teaching Assistant for “Machine Learning” (Fall 2022, Fall 2023, Spring 2024, Spring 2025)
  • Teaching Assistant for “Math for Machine Learning” (Spring 2024)

Services

  • Reviewer for ICLR 2025, ICLR 2026
  • Shadow PC for ICSE 2026

Awards

  • National Scholarship
  • Fifth place in Shanghai Table Tennis Doubles Championship and third place in teams representing my university
  • First Prize in National Olympiad in Physics at High school (Provincial Area)

Materials to share

  • 🔥 A collection of resources for repo-level code generation. [Github]
  • A simple script to detect word by word plagiarism for Academic Writing course in SJTU. [Github]

Thank you for visiting my homepage!