Papers by Collin McMillan
EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention (2026.acl-long)
Copied to clipboard
Yifan Zhang, Chen Huang, Yueke Zhang, Jiahao Zhang, Toby Jia-Jun Li, Collin McMillan, Kevin Leach, Yu Huang
| Challenge: | Code Language Models learn attention based on statistical input-output token correlations. |
| Approach: | They propose a model-agnostic technique to align CodeLLM attention with human visual attention without architectural changes. |
| Outcome: | The proposed model outperforms baselines in three languages, with gains of over 30 CodeBLEU points in translation and up to 22 BERTScore points in summarization. |
Recommendations for Datasets for Source Code Summarization (N19-1)
Copied to clipboard
| Challenge: | Code summarization is the task of writing short, natural language descriptions of source code. |
| Approach: | They propose to use a dataset based on 2.1m pairs of Java methods and one sentence method descriptions from over 28k Java projects to write short, natural language code summarizations. |
| Outcome: | The proposed dataset shows that the proposed standards are more effective than previous versions. |