Paper 2510.23538
JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence
- Published
- Oct 2025
- Research lab
- Independent
- Citations
- 7
- GitHub
- 78 stars
01 In brief
Summary
The paper introduces JANUSCODER, a suite of foundational models for multimodal code intelligence, establishing a unified visual-programmatic interface.
It addresses the scarcity of high-quality multimodal code data by developing a data synthesis toolkit that leverages synergies between data modalities.
This toolkit enables the creation of JANUSCODE-800K, the largest multimodal code corpus to date, covering charts, web UIs, animations, and scientific demonstrations.
The models, JANUSCODER and JANUSCODERV, are trained on this corpus and support generating code from text, visual inputs, or both.
They are evaluated on seven benchmarks, including the newly proposed DTVBENCH for dynamic theorem visualizations.
Results show that the 7B to 14B scale models approach or exceed the performance of commercial models like GPT-4o on both text-centric and vision-centric tasks.
Ablation studies confirm the importance of cross-domain data synergies and reward modeling for data quality.
The work provides a strong open-source foundation for future research in multimodal code intelligence.
02 From the paper
Abstract
The scope of neural code intelligence is rapidly expanding beyond text-based source code to encompass the rich visual outputs that programs generate. This visual dimension is critical for advanced applications like flexible content generation and precise, program-driven editing of visualizations. However, progress has been impeded by the scarcity of high-quality multimodal code data, a bottleneck stemming from challenges in synthesis and quality assessment. To address these challenges, we make contributions from both a data and modeling perspective. We first introduce a complete synthesis toolkit that leverages reciprocal synergies between data modalities to efficiently produce a large-scale, high-quality corpus spanning from standard charts to complex interactive web UIs and code-driven animations. Leveraging this toolkit, we construct JanusCode-800K, the largest multimodal code corpus to date. This powers the training of our models, JanusCoder and JanusCoderV, which establish a visual-programmatic interface for generating code from textual instructions, visual inputs, or a combination of both. Our unified model is a departure from existing approaches that build specialized models for isolated tasks. Extensive experiments on both text-centric and vision-centric coding tasks demonstrate the superior performance of the JanusCoder series, with our 7B to 14B scale models approaching or even exceeding the performance of commercial models. Furthermore, extensive analysis provides key insights into harmonizing programmatic logic with its visual expression. Our code and checkpoints are available at https://github.com/InternLM/JanusCoder.