Cover Image

Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Lei, Zhao, Xuanle, Zeng, Zhixiong, Huang, Jing, Zheng, Liming, Zhong, Yufeng, Ma, Lin
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Chart-R1: Chain-of-Thought Supervision and Reinforcement for Advanced Chart Reasoner
by: Chen, Lei, et al.
Published: (2025)

VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning
by: Zhao, Xuanle, et al.
Published: (2025)

Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR
by: Zhong, Yufeng, et al.
Published: (2025)

OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models
by: Zhong, Yufeng, et al.
Published: (2026)

DocTron-Formula: Generalized Formula Recognition in Complex and Structured Scenarios
by: Zhong, Yufeng, et al.
Published: (2025)

TreeCUA: Efficiently Scaling GUI Automation with Tree-Structured Verifiable Evolution
by: Jiang, Deyang, et al.
Published: (2026)

UItron: Foundational GUI Agent with Advanced Perception and Planning
by: Zeng, Zhixiong, et al.
Published: (2025)

OmniActor: A Generalist GUI and Embodied Agent for 2D&3D Worlds
by: Yang, Longrong, et al.
Published: (2025)

Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning
by: Zhang, Chi, et al.
Published: (2025)

Chart Specification: Structural Representations for Incentivizing VLM Reasoning in Chart-to-Code Generation
by: He, Minggui, et al.
Published: (2026)

DeepSketcher: Internalizing Visual Manipulation for Multimodal Reasoning
by: Zhang, Chi, et al.
Published: (2025)

Improved Iterative Refinement for Chart-to-Code Generation via Structured Instruction
by: Xu, Chengzhi, et al.
Published: (2025)

ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding
by: Huang, Muye, et al.
Published: (2025)

Metis-RISE: RL Incentivizes and SFT Enhances Multimodal Reasoning Model Learning
by: Qiu, Haibo, et al.
Published: (2025)

STAGE: Stable and Generalizable GRPO for Autoregressive Image Generation
by: Ma, Xiaoxiao, et al.
Published: (2025)

Learning When to Look: A Disentangled Curriculum for Strategic Perception in Multimodal Reasoning
by: Yang, Siqi, et al.
Published: (2025)

Contrastive Learning for Multimodal Human Activity Recognition with Limited Labeled Data
by: Jing, Long, et al.
Published: (2026)

Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy
by: Ma, Xiaoxiao, et al.
Published: (2025)

Advancing Multimodal Large Language Models in Chart Question Answering with Visualization-Referenced Instruction Tuning
by: Zeng, Xingchen, et al.
Published: (2024)

OneChart: Purify the Chart Structural Extraction via One Auxiliary Token
by: Chen, Jinyue, et al.
Published: (2024)

OpusAnimation: Code-Based Dynamic Chart Generation
by: Li, Bozheng, et al.
Published: (2025)

CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution
by: Zheng, Xiangxi, et al.
Published: (2026)

Chart-RVR: Reinforcement Learning with Verifiable Rewards for Explainable Chart Reasoning
by: Sinha, Sanchit, et al.
Published: (2025)

InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts
by: Xie, Tianchi, et al.
Published: (2025)

Metis-SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start
by: Chen, Kun, et al.
Published: (2025)

Benchmarking Multimodal RAG through a Chart-based Document Question-Answering Generation Framework
by: Yang, Yuming, et al.
Published: (2025)

ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation
by: Yang, Cheng, et al.
Published: (2024)

ChartGen: Scaling Chart Understanding Via Code-Guided Synthetic Chart Generation
by: Kondic, Jovana, et al.
Published: (2025)

From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation
by: Niu, Ke, et al.
Published: (2025)

ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation
by: Zhao, Xuanle, et al.
Published: (2025)

MSG-Chart: Multimodal Scene Graph for ChartQA
by: Dai, Yue, et al.
Published: (2024)

TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks
by: Zhao, Xuanle, et al.
Published: (2025)

ChartAct: A Benchmark for Dynamic Chart Understanding
by: Huang, Muye, et al.
Published: (2026)

Manifold-Aware Exploration for Reinforcement Learning in Video Generation
by: Zheng, Mingzhe, et al.
Published: (2026)

Visual Programmability: A Guide for Code-as-Thought in Chart Understanding
by: Tang, Bohao, et al.
Published: (2025)

SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL
by: Wang, Junke, et al.
Published: (2025)

OmniHD-Scenes: A Next-Generation Multimodal Dataset for Autonomous Driving
by: Zheng, Lianqing, et al.
Published: (2024)

ChartM$^3$: Benchmarking Chart Editing with Multimodal Instructions
by: Yang, Donglu, et al.
Published: (2025)

Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
by: Wang, Sudong, et al.
Published: (2026)

ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning
by: Meng, Fanqing, et al.
Published: (2024)