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

TL;DR

This paper introduces C2C-MoLA, a multimodal framework combining Mixture of Experts and Low-Rank Adaptation to improve chart-to-code generation, achieving higher accuracy, efficiency, and scalability on complex charts.

Contribution

It presents a novel adaptive expert routing mechanism with domain-specific experts and resource-efficient training strategies for improved multimodal code generation.

Findings

Up to 17% increase in generation accuracy

18% reduction in peak GPU memory usage

20% faster convergence during training

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.