Fengzhi Li — accepted AI-conference papers

2026

Strategy-Aware Optimization Modeling with Reasoning LLMs

Ruiqing Zhao, Fengzhi Li, Yuan Zuo, Rui Liu, YanSong Liu, Yunfei Ma +2

ICML 2026poster

Large language models (LLMs) can generate syntactically valid optimization programs, yet often struggle to reliably choose an effective modeling strategy, leading to incorrect formulations and inefficient solver behavior. We propose **SAGE**, a strategy-aware framework that makes *Modeling Strategy*…

Cited by 0 Source ↗Scholar ↗

2024

LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings

Duo Wang, Yuan Zuo, Fengzhi Li, Junjie Wu

NeurIPS 2024poster

Zero-shot graph machine learning, especially with graph neural networks (GNNs), has garnered significant interest due to the challenge of scarce labeled data. While methods like self-supervised learning and graph prompt learning have been extensively explored, they often rely on fine-tuning with tas…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗