Seeing Is Coding: On the Effectiveness of Vision Language Models in Code Understanding
Large Language Models (LLMs) have achieved remarkable success in source code understanding, yet as software systems grow in scale, computational efficiency has become a critical bottleneck. Currently, these models rely on a text-based paradigm that treats source code as a linear sequence of tokens, which leads to a lin...
Yanan Shi, Chaoxiang Xie, Zhensu Sun et al.
· Proceedings of the ACM on so... · 1 citation