Jiayi Lu — accepted AI-conference papers

2026

AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions

Zihan Wang, Jiaze Chen, Zhicheng Liu, Haojie Pan, Markus Mak, Yidi Du +20

ICLR 2026poster

Competitive programming has emerged as a critical benchmark for evaluating the reasoning and coding capabilities of Large Language Models (LLMs). Despite impressive progress on existing benchmarks, we argue that current evaluations overstate model proficiency, masking a substantial gap between LLMs…

Cited by 0 Source ↗Scholar ↗

2026

“The Whole Is Greater than the Sum of Its Parts”: A Compatibility-Aware Multi-Teacher CoT Distillation Framework

Jin Cui, Jiaqi Guo, Ruixuan Yang, Jiayi Lu, Jiepeng Zhou, Jiajun Xu +3

IJCAI 2026

Chain-of-Thought (CoT) reasoning empowers Large Language Models (LLMs) with remarkable capabilities but typically requires prohibitive parameter scales. CoT distillation has emerged as a promising paradigm to transfer reasoning prowess into compact Student Models (SLMs), but existing approaches ofte

Cited by 0 Scholar ↗