Zhiyi Wei — accepted AI-conference papers

2026

From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph

Junfeng Gong, Zhiyi Wei, Junying Chen, Cheng Liu, Huawei Li

ICLR 2026poster

Despite significant evolution of CUDA programming and domain-specific libraries, effectively utilizing GPUs with massively parallel engines remains difficult. Large language models (LLMs) show strong potential in generating optimized CUDA code from sequential code. However, using LLMs in practice fa…

Cited by 0 Source ↗Scholar ↗

2024

A Coarse-to-Fine Prototype Learning Approach for Multi-Label Few-Shot Intent Detection

Xiaotong Zhang, Xinyi Li, Feng Zhang, Zhiyi Wei, Junfeng Liu, Han Liu

EMNLP 2024finding

Few-shot intent detection is a challenging task, particularly in scenarios involving multiple labels and diverse domains. This paper presents a novel prototype learning approach that combines the label synset augmentation and the coarse-to-fine prototype distillation for multi-label few-shot intent…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗