collaborators

6 papers

cs.AI2026

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

MiniMax, :, Aili Chen +219

We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The…

cs.SE2026

Contextualized Code Pretraining for Code Generation

Chen Liu, Qingyuan Liang, Hanwen Zhang +3

As code generation becomes increasingly central to improving software development efficiency, modern code models are largely trained and evaluated on code with natural-language des…

cs.SE2026

TRACE: Evaluating Execution Efficiency of LLM-Based Code Translation

Zhihao Gong, Zeyu Sun, Dong Huang +3

While Large Language Models (LLMs) have substantially improved the functional correctness of code translation, the critical dimension of \textit{execution efficiency} remains overl…

cs.SE2026

TRACE: Evaluating Execution Efficiency of LLM-Based Code Translation

Zhihao Gong, Zeyu Sun, Dong Huang +3

While Large Language Models (LLMs) have substantially improved the functional correctness of code translation, the critical dimension of \textit{execution efficiency} remains overl…

cs.SE2025

DSCodeBench: A Realistic Benchmark for Data Science Code Generation

Shuyin Ouyang, Dong Huang, Jingwen Guo +3

We introduce DSCodeBench, a new benchmark designed to evaluate large language models (LLMs) on complicated and realistic data science code generation tasks. DSCodeBench consists of…

cs.SE2025

Knowledge-Enhanced Program Repair for Data Science Code

Shuyin Ouyang, Jie M. Zhang, Zeyu Sun +1

This paper introduces DSrepair, a knowledge-enhanced program repair method designed to repair the buggy code generated by LLMs in the data science domain. DSrepair uses knowledge g…