Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning

• URL: http://arxiv.org/abs/2604.06079v1
• Date: Tue, 07 Apr 2026 16:58:14 GMT
• Title: Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning
• Abstract summary: We present a closed-loop framework featuring SciTikZ-230K, a large-scale, high-quality dataset from our Execution-Centric Data Engine.<n>Our trained model SciTikZer-8B achieves state-of-the-art performance, consistently outperforming proprietary giants like Gemini-2.5-Pro and massive models like Qwen3-VL-235B-A22B-Instruct.
• Score: 36.86798995699176
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graphics Program Synthesis is pivotal for interpreting and editing visual data, effectively facilitating the reverse-engineering of static visuals into editable TikZ code. While TikZ is the de facto standard for scientific schematics due to its programmatic flexibility, its requirement for rigorous spatial precision presents a significant challenge for Multimodal Large Language Models. Progress is currently stifled by two primary gaps: (1) Data Quality Gap: existing image-TikZ corpora often lack strict executability and reliable visual alignment; (2) Evaluation Gap: a lack of benchmarks for both structural and visual fidelity. To address these, we present a closed-loop framework featuring: SciTikZ-230K, a large-scale, high-quality dataset from our Execution-Centric Data Engine covering 11 diverse scientific disciplines; SciTikZ-Bench, a multifaceted benchmark spanning from basic geometric constructs to intricate hierarchical schematics to evaluate both visual fidelity and structural logic. To further broaden the scope of visual-code optimization methodology, we introduce a novel Dual Self-Consistency Reinforcement Learning optimization paradigm, which utilizes Round-Trip Verification to penalize degenerate code and boost overall self-consistency. Empowered by these, our trained model SciTikZer-8B achieves state-of-the-art performance, consistently outperforming proprietary giants like Gemini-2.5-Pro and massive models like Qwen3-VL-235B-A22B-Instruct.

Related papers

• Faithful, Enriched, and Precise: Benchmarking Natural-Science Illustration Generation by T2I models [49.93401412148884]
  We introduce FEPBench, a benchmark built from carefully selected high-quality scientific illustrations.<n>We evaluate T2I models along three dimensions: instruction faithfulness, reasoning enrichment, and semantic precision.<n>Results show that even state-of-the-art closed-source models, such as GPT Image 2 and Nano Banana Pro, still suffer from text-rendering bottlenecks, limited reasoning enrichment, and difficulty balancing generation richness with precision.
  arXiv  Detail & Related papers  (2026-06-04T09:49:02Z)
• Omni-I2C: A Holistic Benchmark for High-Fidelity Image-to-Code Generation [59.87131391492088]
  We present Omni-I2C, a benchmark designed to evaluate the capability of Large Multimodal Models (LMMs) in converting complex, structured digital graphics into executable code.<n>By incorporating authentic user-sourced cases, the benchmark spans a vast spectrum of digital content.<n>Our evaluation reveals a substantial performance gap among leading LMMs.
  arXiv  Detail & Related papers  (2026-03-18T09:10:04Z)
• Thinking with Programming Vision: Towards a Unified View for Thinking with Images [23.596757163808906]
  We show that even state-of-the-art MLLMs are surprisingly brittle, showing significant performance degradation on images with simple orientation changes or natural corruptions.<n>We propose CodeVision, a flexible and scalable code-as-tool framework where the model generates code as a universal interface to invoke any image operation.
  arXiv  Detail & Related papers  (2025-12-03T12:44:15Z)
• IAR2: Improving Autoregressive Visual Generation with Semantic-Detail Associated Token Prediction [77.06211178777939]
  IAR2 is an advanced autoregressive framework that enables a hierarchical semantic-detail synthesis process.<n>We show that IAR2 sets a new state-of-the-art for autoregressive image generation, achieving a FID of 1.50 on ImageNet.
  arXiv  Detail & Related papers  (2025-10-08T12:08:21Z)
• Robust Diagram Reasoning: A Framework for Enhancing LVLM Performance on Visually Perturbed Scientific Diagrams [0.81996963503528]
  Large Language Models (LLMs) and their multimodal variants (LVLMs) hold immense promise for scientific and engineering applications.<n>Existing evaluation benchmarks largely overlook this challenge, leaving the robust reasoning capabilities of LVLMs underexplored.<n>We introduce the Robust Diagram Reasoning (RDR) framework, a novel approach designed to enhance and rigorously evaluate LVLMs' performance under such conditions.
  arXiv  Detail & Related papers  (2025-08-23T09:50:58Z)
• 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)
• 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)
• S^2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in OR [50.435592120607815]
  Scene graph generation (SGG) of surgical procedures is crucial in enhancing holistically cognitive intelligence in the operating room (OR) Previous works have primarily relied on multi-stage learning, where the generated semantic scene graphs depend on intermediate processes with pose estimation and object detection. In this study, we introduce a novel single-stage bi-modal transformer framework for SGG in the OR, termed S2Former-OR.
  arXiv  Detail & Related papers  (2024-02-22T11:40:49Z)
• CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning [61.21923643289266]
  Chain of Manipulations is a mechanism that enables Vision-Language Models to solve problems step-by-step with evidence.<n>After training, models can solve various visual problems by eliciting intrinsic manipulations (e.g., grounding, zoom in) actively without involving external tools.<n>Our trained model, textbfCogCoM, achieves state-of-the-art performance across 9 benchmarks from 4 categories.
  arXiv  Detail & Related papers  (2024-02-06T18:43:48Z)
• SGTR+: End-to-end Scene Graph Generation with Transformer [42.396971149458324]
  Scene Graph Generation (SGG) remains a challenging visual understanding task due to its compositional property. Most previous works adopt a bottom-up, two-stage or point-based, one-stage approach, which often suffers from high time complexity or suboptimal designs. We propose a novel SGG method to address the aforementioned issues, formulating the task as a bipartite graph construction problem.
  arXiv  Detail & Related papers  (2024-01-23T15:18:20Z)

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.