← Search

Dong Jinyuan

2 accepted papers

2026

Behavioral Embeddings of Programs: A Quasi-Dynamic Approach for Optimization Prediction

ICLR 2026poster

Learning effective numerical representations, or embeddings, of programs is a fundamental prerequisite for applying machine learning to automate and enhance compiler optimization. Prevailing paradigms, however, present a dilemma. Static representations, derived from source code or intermediate repre…

Cited by 0SourcecodeScholar
2026

ECCO: Evidence-Driven Causal Reasoning for Compiler Optimization

ICML 2026poster

Compiler auto-tuning faces a dichotomy between traditional black-box search methods, which lack semantic guidance, and recent Large Language Model (LLM) approaches, which often suffer from superficial pattern matching and causal opacity. In this paper, we introduce ECCO, a framework that bridges int…

Cited by 0SourceScholar