Zhilei Chai — accepted AI-conference papers

2026

CIRBench: Evaluating Large Language Models as LLVM IR Optimizers

Zi Yang, Haifeng Ding, Fei Liu, Yingying Cheng, Han Cheng, Zhilei Chai +1

ICML 2026spotlight

Large language models are beginning to introduce a new paradigm for compilation: instead of only assisting at the source level, they can operate directly on **intermediate representations (IRs)**, the compiler’s internal code representation, Early studies suggest that LLM-guided optimization can som…

Cited by 0 Source ↗Scholar ↗

2025

IR-OptSet: An Optimization-Sensitive Dataset for Advancing LLM-Based IR Optimizer

Zi Yang, Lei Qiu, FANG LYU, Ming Zhong, Zhilei Chai, Haojie Zhou +2

NeurIPS 2025poster

Compiler optimization is essential for improving program performance, yet modern compilers still depend on manually crafted transformation rules over intermediate representations (IRs). As compilers grow in complexity, maintaining these rule-based optimizations becomes increasingly labor-intensive a…

Cited by 0 Source ↗Scholar ↗