English

Chart2Code-MoLA: Efficient Multi-Modal Code Generation via Adaptive Expert Routing

Software Engineering 2025-12-01 v1

Abstract

Chart-to-code generation is a critical task in automated data visualization, translating complex chart structures into executable programs. While recent Multi-modal Large Language Models (MLLMs) improve chart representation, existing approaches still struggle to achieve cross-type generalization, memory efficiency, and modular design. To address these challenges, this paper proposes C2C-MoLA, a multimodal framework that synergizes Mixture of Experts (MoE) with Low-Rank Adaptation (LoRA). The MoE component uses a complexity-aware routing mechanism with domain-specialized experts and load-balanced sparse gating, dynamically allocating inputs based on learnable structural metrics like element count and chart complexity. LoRA enables parameter-efficient updates for resource-conscious tuning, further supported by a tailored training strategy that aligns routing stability with semantic accuracy. Experiments on Chart2Code-160k show that the proposed model improves generation accuracy by up to 17%, reduces peak GPU memory by 18%, and accelerates convergence by 20%, when compared to standard fine-tuning and LoRA-only baselines, particularly on complex charts. Ablation studies validate optimal designs, such as 8 experts and rank-8 LoRA, and confirm scalability for real-world multimodal code generation.

Keywords

Cite

@article{arxiv.2511.23321,
  title  = {Chart2Code-MoLA: Efficient Multi-Modal Code Generation via Adaptive Expert Routing},
  author = {Yifei Wang and Jacky Keung and Zhenyu Mao and Jingyu Zhang and Yuchen Cao},
  journal= {arXiv preprint arXiv:2511.23321},
  year   = {2025}
}
R2 v1 2026-07-01T07:59:40.237Z