VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning

arXiv:2511.00391v3 Announce Type: replace Abstract: While recent specialized multimodal code generation models excel in tasks like chart-to-code generation, their reliance on single-task training limits generalization and hinders the development of extbf{VI}sioextbf{N} extbf{C}ode extbf{I}ntelligence. In this work, we introduce extbf{VinciCoder}, a unified framework designed for generalized multimodal code generation. We first curate a large-scale SFT corpus comprising 1.3M direct generation pairs and 300k visual-based refinement tasks. This composition fosters self-refinement capabilities, enabling the model to directly rectify code to align with input images. Subsequently, we propose coarse-to-fine Visual Reinforcement Learning (ViRL) to overcome the brittleness of textual metrics in handling semantically equivalent but syntactically diverse code. By quantifying visual similarity across multi-scale patches, ViRL provides an implementation-agnostic reward mechanism that ensures high-fidelity alignment between rendered outputs and input visuals. Extensive experimental results across diverse benchmarks demonstrate that VinciCoder achieves superior performance, while comprehensive ablation studies validate the effectiveness of our proposed ViRL strategy. The data, code and model are available at https://github.com/DocTron-hub/VinciCoder.

Source: arXiv cs.CV | 2026-08-25