{"total":74,"rows":[{"id":"2601.11109","title":"Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning","created":"2026-01-16","cited_by_count":49,"area":"lr"},{"id":"2511.00391","title":"VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning","created":"2025-11-01","cited_by_count":21,"area":null},{"id":"2506.03139","title":"SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation","created":"2025-06-03","cited_by_count":16,"area":"mllm"},{"id":"2511.02778","title":"VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation","created":"2025-11-04","cited_by_count":16,"area":null},{"id":"2508.07766","title":"UniSVG: A Unified Dataset for Vector Graphic Understanding and Generation with Multimodal Large Language Models","created":"2025-08-11","cited_by_count":15,"area":"mllm"},{"id":"2510.11341","title":"InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models","created":"2025-10-13","cited_by_count":14,"area":"mllm"},{"id":"2603.06674","title":"AutoFigure-Edit: Generating Editable Scientific Illustration","created":"2026-03-03","cited_by_count":14,"area":null},{"id":"2603.13032","title":"Multimodal OCR: Parse Anything from Documents","created":"2026-03-13","cited_by_count":14,"area":null},{"id":"2601.21639","title":"OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models","created":"2026-01-29","cited_by_count":12,"area":"mllm"},{"id":"2604.20730","title":"Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback","created":"2026-04-22","cited_by_count":12,"area":"mllm"},{"id":"2605.30248","title":"GenClaw: Code-Driven Agentic Image Generation","created":"2026-05-28","cited_by_count":11,"area":"agents"},{"id":"2510.23538","title":"JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence","created":"2025-10-27","cited_by_count":9,"area":null},{"id":"2512.10894","title":"DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidance","created":"2025-12-11","cited_by_count":8,"area":"mllm"},{"id":"2509.05208","title":"Symbolic Graphics Programming with Large Language Models","created":"2025-09-05","cited_by_count":7,"area":null},{"id":"2602.13294","title":"VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction","created":"2026-02-09","cited_by_count":7,"area":"lr"},{"id":"2605.01517","title":"VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation","created":"2026-05-02","cited_by_count":6,"area":null},{"id":"2505.16832","title":"From EduVisBench to EduVisAgent: A Benchmark and Multi-Agent Framework for Reasoning-Driven Pedagogical Visualization","created":"2025-05-22","cited_by_count":5,"area":"lr"},{"id":"2505.19492","title":"ViewCraft3D: High-Fidelity and View-Consistent 3D Vector Graphics Synthesis","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2603.29590","title":"Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration","created":"2026-02-06","cited_by_count":5,"area":null},{"id":"2603.29852","title":"VectorGym: A Multi-Task Benchmark for SVG Code Generation, Sketching and Editing","created":"2026-02-22","cited_by_count":5,"area":null},{"id":"2604.11792","title":"LottieGPT: Tokenizing Vector Animation for Autoregressive Generation","created":"2026-04-13","cited_by_count":5,"area":null},{"id":"2510.27452","title":"From Pixels to Paths: A Multi-Agent Framework for Editable Scientific Illustration","created":"2025-10-31","cited_by_count":4,"area":"agents"},{"id":"2603.09312","title":"IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic Framework","created":"2026-03-10","cited_by_count":4,"area":"alignment"},{"id":"2603.24575","title":"VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models","created":"2026-03-25","cited_by_count":4,"area":null},{"id":"2604.05514","title":"OmniDiagram: Advancing Unified Diagram Code Generation via Visual Interrogation Reward","created":"2026-04-07","cited_by_count":4,"area":null},{"id":"2605.11307","title":"Vision2Code: A Multi-Domain Benchmark for Evaluating Image-to-Code Generation","created":"2026-05-11","cited_by_count":4,"area":"mllm"},{"id":"2602.21461","title":"VecGlypher: Unified Vector Glyph Generation with Language Models","created":"2026-02-25","cited_by_count":3,"area":null},{"id":"2603.02138","title":"OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2603.10757","title":"CodePercept: Code-Grounded Visual STEM Perception for MLLMs","created":"2026-03-11","cited_by_count":3,"area":"lr"},{"id":"2603.13224","title":"Visual-ERM: Reward Modeling for Visual Equivalence","created":"2026-03-13","cited_by_count":3,"area":"alignment"},{"id":"2603.22687","title":"GeoTikzBridge: Advancing Multimodal Code Generation for Geometric Perception and Reasoning","created":"2026-03-24","cited_by_count":3,"area":"lr"},{"id":"2604.10940","title":"AmodalSVG: Amodal Image Vectorization via Semantic Layer Peeling","created":"2026-04-13","cited_by_count":3,"area":null},{"id":"2510.22684","title":"RoboSVG: A Unified Framework for Interactive SVG Generation with Multi-modal Guidance","created":"2025-10-26","cited_by_count":2,"area":null},{"id":"2512.14336","title":"Vector Prism: Animating Vector Graphics by Stratifying Semantic Structure","created":"2025-12-16","cited_by_count":2,"area":null},{"id":"2602.06090","title":"SVRepair: Structured Visual Reasoning for Automated Program Repair","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2603.14505","title":"Unlocking the Latent Canvas: Eliciting and Benchmarking Symbolic Visual Expression in LLMs","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2605.25447","title":"GeoSVG-RL: Geometry-Aware Reinforcement Learning for Layout-Constrained Text-to-SVG Diagram Generation","created":"2026-05-25","cited_by_count":2,"area":"deeprl"},{"id":"2605.30174","title":"LiveSVG: Zero-Shot SVG Animation via Video Generation","created":"2026-05-28","cited_by_count":2,"area":"diffusion"},{"id":"2607.15272","title":"SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions","created":"2026-07-16","cited_by_count":2,"area":null},{"id":"2609.01006","title":"Figures as Programs: Recursive Generation of Editable Scientific Figures","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2509.22151","title":"MultiMat: Multimodal Program Synthesis for Procedural Materials using Large Multimodal Models","created":"2025-09-26","cited_by_count":1,"area":"mllm"},{"id":"2511.17454","title":"Illustrator's Depth: Monocular Layer Index Prediction for Image Decomposition","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2604.05072","title":"Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2604.08809","title":"Structural Evaluation Metrics for SVG Generation via Leave-One-Out Analysis","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2604.17054","title":"mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrieval","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2605.19382","title":"PRISM: A Benchmark for Programmatic Spatial-Temporal Reasoning","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2605.19551","title":"AnchorFlow: Learning Anchor Placement for Faithful and Editable SVG Reconstruction","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2607.25565","title":"ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2608.00548","title":"DrawAI: Agentic Benchmark and Workflow for Making Raster Images Editable","created":"2026-08-01","cited_by_count":1,"area":"agents"},{"id":"2608.01977","title":"SVGEval: A Vision-Grounded Framework for Perceptual-Quality Benchmarking and Evaluation in Text-to-SVG Generation","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2608.08964","title":"Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities","created":"2026-08-09","cited_by_count":1,"area":null},{"id":"2608.21893","title":"A Scalable Vector Graphics Latent Space","created":"2026-08-22","cited_by_count":1,"area":null},{"id":"2609.25270","title":"RULER: Instance-aware Rubric Rewards for SVG Generation","created":"2026-09-21","cited_by_count":1,"area":"alignment"},{"id":"2509.18948","title":"One-shot Embroidery Customization via Contrastive LoRA Modulation","created":"2025-09-23","cited_by_count":0,"area":"diffusion"},{"id":"2511.20034","title":"Clair Obscur: an Illumination-Aware Method for Real-World Image Vectorization","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2602.02820","title":"From Tokens to Numbers: Continuous Number Modeling for SVG Generation","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2604.15663","title":"CodeMMR: Bridging Natural Language, Code, and Image for Unified Retrieval","created":"2026-04-17","cited_by_count":0,"area":"rag"},{"id":"2605.24398","title":"VectorArk: Learning Practical Image Vectorization with Rounded Polygon Representation","created":"2026-05-23","cited_by_count":0,"area":"mllm"},{"id":"2606.26299","title":"COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.03530","title":"MentalThink: Shaping Thoughts in Mental SVG World","created":"2026-07-03","cited_by_count":0,"area":"lr"},{"id":"2607.17251","title":"VecFontLLM: Anchor-Guided Direct Synthesis of Chinese Vector Fonts","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2607.27699","title":"RefineSVG: Visual Feedback-Driven Reinforcement Learning for Image-to-SVG Generation","created":"2026-07-30","cited_by_count":0,"area":"mllm"},{"id":"2608.05478","title":"GenGA: Editable and Data-Grounded Graphical Abstract Generation for Academic Papers","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.12064","title":"Draw This First","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.21659","title":"SketchFlow: Zero-Shot Vector Sketch Generation via GMM Prior Flow in CLIP Latent Space","created":"2026-08-21","cited_by_count":0,"area":"diffusion"},{"id":"2608.26544","title":"Chart2SVG: Editable SVG Generation from Raster Chart Images","created":"2026-08-27","cited_by_count":0,"area":"mllm"},{"id":"2608.28678","title":"Evaluating Constrained Iterative Refinement for Scalable Vector Graphics Generation with Off-the-Shelf VLMs","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.30689","title":"CANVAS: Consistency-Aware Navigation via Visual Adaptive Sampling for Long-Context Text-to-SVG Generation","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.03806","title":"SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generation","created":"2026-09-03","cited_by_count":0,"area":"alignment"},{"id":"2609.04034","title":"Editable Visual Design","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.14657","title":"Compositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing","created":"2026-09-13","cited_by_count":0,"area":"lr"},{"id":"2609.34587","title":"Reinforcement Learning from Intermediate Renders for Image-to-Code Generation","created":"2026-09-28","cited_by_count":0,"area":"mllm"},{"id":"2610.19025","title":"How Far Can Coding Agents Go in Visual Generation?","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.20538","title":"PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}