Scholar
Peng Di
Google Scholar ID: TluY-G0AAAAJ
Senior Staff Engineer at Ant Group; Adjunct Associate Professor at UNSW Sydney
Citations & Impact
Citations
462
H-index
10
i10-index
11
Publications
20
Co-authors
21
list available
Publications
Resume (English only)
Academic Achievements
- Publications: 'BIT: Empowering Binary Analysis Through the LLVM Toolchain' accepted by CGO 2026, 'Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks' accepted by NeurIPS 2025, 'Evolving Trends, Patterns, and Hidden Pitfalls: Unveiling JavaScript Feature Usage in the Wild' accepted by ICSE 2026, etc.; Open-source projects: CodeFuse, Ling-Coder-Lite (based on the Ant Ling-MoE architecture), OpenDeRisk (an AI-native risk intelligence system); Awards: 'Tumbling Down the Rabbit Hole: How do Assisting Exploration Strategies Facilitate Grey-box Fuzzing?' won ACM SIGSOFT Distinguished Paper Award.
Research Experience
- Worked as a Research Associate at Compiler Research Group, co-developed an inter-procedural dependence analysis tool SVF; Served as a Technical Expert of AI compiler at Huawei, founder of MindSpore/AKG (an open-sourced AI compiler for Huawei Ascend 910); Currently leading a team at AntGroup that integrates Large Language Models into real-world industrial scenarios to enhance the effectiveness and efficiency of software development.
Education
- PhD degree from UNSW, supervised by Scientia Professor Jingling Xue
Background
- Research Interests: Large Language Model, AI Software Engineering, Programming Language, Program Analysis, Software Security, Parallel Programming and Optimizations for Heterogeneous Systems. Brief Introduction: Working as a Senior Staff Engineer at Ant Group, leading the Intelligent Platform Engineering team; also an Adjunct Associate Professor at the University of New South Wales and an Industrial PhD Mentor at Zhejiang University.
Miscellany
- Personal interests not specified
