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

• URL: http://arxiv.org/abs/2511.00391v1
• Date: Sat, 01 Nov 2025 04:05:26 GMT
• Title: VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning
• Authors: Xuanle Zhao, Deyang Jiang, Zhixiong Zeng, Lei Chen, Haibo Qiu, Jing Huang, Yufeng Zhong, Liming Zheng, Yilin Cao, Lin Ma,
• Abstract summary: We introduce textbfciCoder, a unified multimodal code generation model.<n>We begin by constructing a large-scale Supervised Finetuning (SFT) corpus comprising 1.6M image-code pairs.<n>We then introduce a Visual Reinforcement Learning (ViRL) strategy, which employs a coarse-to-fine reward mechanism to improve visual fidelity.
• Score: 13.193184888476404
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Multimodal code generation has garnered significant interest within the research community. Despite the notable success of recent vision-language models (VLMs) on specialized tasks like Chart-to-code generation, their reliance on single-task training regimens fosters a narrow paradigm that hinders the development of generalized \textbf{VI}sio\textbf{N} \textbf{C}ode \textbf{I}ntelligence. In this work, we introduce \textbf{VinciCoder}, a unified multimodal code generation model that addresses this limitation via a two-stage training framework. We begin by constructing a large-scale Supervised Finetuning (SFT) corpus comprising 1.6M image-code pairs for tasks involving direct code generation and visual-based code refinement. Subsequently, we introduce a Visual Reinforcement Learning (ViRL) strategy, which employs a coarse-to-fine reward mechanism to improve visual fidelity by calculating visual similarity across local and global image patches. Extensive experiments on various multimodal code generation benchmarks demonstrate that VinciCoder achieves state-of-the-art performance, underscoring the effectiveness of our coarse-to-fine ViRL strategy. The code and model will be available at https://github.com/DocTron-hub/VinciCoder.

Related papers

• CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding [71.88471147281406]
  We propose an auto-regressive generation approach, CausalEmbed, for constructing multi-vector embeddings.<n>By incorporating iterative margin loss during contrastive training, CausalEmbed encourages embedding models to learn compact and well-structured representations.<n>Our method enables efficient VDR tasks using only dozens of visual tokens, achieving a 30-155x reduction in token count.
  arXiv  Detail & Related papers  (2026-01-29T04:47:27Z)
• ThinkGen: Generalized Thinking for Visual Generation [97.19923474851987]
  ThinkGen is a think-driven visual generation framework that explicitly leverages Chain-of-Thought (CoT) reasoning in various generation scenarios.<n>We propose a separable GRPO-based training paradigm, alternating reinforcement learning between the MLLM and DiT modules.<n>Experiments demonstrate that ThinkGen achieves robust, state-of-the-art performance across multiple generation benchmarks.
  arXiv  Detail & Related papers  (2025-12-29T16:08:50Z)
• JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence [48.39202336809688]
  We introduce a complete synthesis toolkit to efficiently produce a large-scale, high-quality corpus spanning from standard charts to complex interactive web UIs and code-driven animations.<n>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.<n>Our 7B to 14B scale models approaching or even exceeding the performance of commercial models.
  arXiv  Detail & Related papers  (2025-10-27T17:13:49Z)
• CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images [69.93976232543066]
  We propose CodePlot-CoT, a code-driven Chain-of-Thought paradigm for "thinking with images" in mathematics.<n>To achieve this, we first construct Math-VR, the first large-scale, bilingual dataset and benchmark for Mathematics problems with Visual Reasoning.<n>Our model achieves up to 21% increase over base model on our new benchmark, fully validating the efficacy of our proposed code-driven reasoning paradigm.
  arXiv  Detail & Related papers  (2025-10-13T17:59:55Z)
• Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation [12.822184232115333]
  We propose Multimodal Structured Reinforcement Learning (MSRL) for chart-to-code generation.<n>We construct the largest training corpus to date, containing 3 million chart-code pairs from real-world arXiv tables.<n>MSRL significantly breaks the SFT plateau, improving high-level metrics by 6.2% and 9.9% on ChartMimic and ReachQA benchmarks respectively.
  arXiv  Detail & Related papers  (2025-08-19T07:40:18Z)
• VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models [82.05514464090172]
  Multimodal large language models (MLLMs) have significantly advanced the integration of visual and textual understanding.<n>However, their ability to generate code from multimodal inputs remains limited.<n>We introduce VisCodex, a unified framework that seamlessly merges vision and coding language models.
  arXiv  Detail & Related papers  (2025-08-13T17:00:44Z)
• ScreenCoder: Advancing Visual-to-Code Generation for Front-End Automation via Modular Multimodal Agents [40.697759330690815]
  ScreenCoder is a modular multi-agent framework that decomposes the task into three interpretable stages: grounding, planning, and generation.<n>By assigning these distinct responsibilities to specialized agents, our framework achieves significantly higher robustness and fidelity than end-to-end approaches.<n>Our approach achieves state-of-the-art performance in layout accuracy, structural coherence, and code correctness.
  arXiv  Detail & Related papers  (2025-07-30T16:41:21Z)
• Boosting Chart-to-Code Generation in MLLM via Dual Preference-Guided Refinement [16.22363384653305]
  Multimodal Large Language Models (MLLMs) perform fine-grained visual parsing, precise code synthesis, and robust cross-modal reasoning.<n>We propose a dual preference-guided refinement framework that combines a feedback-driven, dual-modality reward mechanism with iterative preference learning.<n>Our framework significantly enhances the performance of general-purpose open-source MLLMs, enabling them to generate high-quality plotting code.
  arXiv  Detail & Related papers  (2025-04-03T07:51:20Z)
• Harmonizing Visual Representations for Unified Multimodal Understanding and Generation [53.01486796503091]
  We present emphHarmon, a unified autoregressive framework that harmonizes understanding and generation tasks with a shared MAR encoder.<n>Harmon achieves state-of-the-art image generation results on the GenEval, MJHQ30K and WISE benchmarks.
  arXiv  Detail & Related papers  (2025-03-27T20:50:38Z)
• Code Representation Learning At Scale [75.04686476303436]
  We fuel code representation learning with a vast amount of code data via a two-stage pretraining scheme. We first train the encoders via a mix that leverages both randomness in masking language modeling and the structure aspect of programming language. We then enhance the representations via contrastive learning with hard negative and hard positive constructed in an unsupervised manner.
  arXiv  Detail & Related papers  (2024-02-02T22:19:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.