{"total":152,"rows":[{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793,"area":"mllm"},{"id":"2501.06598","title":"ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation","created":"2025-01-11","cited_by_count":92,"area":"mllm"},{"id":"2409.20566","title":"MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning","created":"2024-09-30","cited_by_count":76,"area":"mllm"},{"id":"2505.21497","title":"Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers","created":"2025-05-27","cited_by_count":63,"area":null},{"id":"2604.26752","title":"GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents","created":"2026-04-29","cited_by_count":34,"area":"agents"},{"id":"2601.09668","title":"STEP3-VL-10B Technical Report","created":"2026-01-14","cited_by_count":32,"area":null},{"id":"2505.17399","title":"FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow","created":"2025-05-23","cited_by_count":28,"area":null},{"id":"2605.27365","title":"LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding","created":"2026-05-26","cited_by_count":28,"area":"mllm"},{"id":"2601.04126","title":"InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training","created":"2026-01-07","cited_by_count":27,"area":"agents"},{"id":"2507.22827","title":"ScreenCoder: Advancing Visual-to-Code Generation for Front-End Automation via Modular Multimodal Agents","created":"2025-07-30","cited_by_count":26,"area":"agents"},{"id":"2505.20139","title":"StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs","created":"2025-05-26","cited_by_count":25,"area":null},{"id":"2412.15310","title":"MRWeb: An Exploration of Generating Multi-Page Resource-Aware Web Code from UI Designs","created":"2024-12-19","cited_by_count":24,"area":null},{"id":"2510.10991","title":"A Survey on Agentic Multimodal Large Language Models","created":"2025-10-13","cited_by_count":23,"area":"mllm"},{"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":"2410.12381","title":"HumanEval-V: Benchmarking High-Level Visual Reasoning with Complex Diagrams in Coding Tasks","created":"2024-10-16","cited_by_count":20,"area":"lr"},{"id":"2506.13832","title":"FrontendBench: A Benchmark for Evaluating LLMs on Front-End Development via Automatic Evaluation","created":"2025-06-16","cited_by_count":20,"area":null},{"id":"2510.22780","title":"How Do AI Agents Do Human Work? Comparing AI and Human Workflows Across Diverse Occupations","created":"2025-10-26","cited_by_count":19,"area":null},{"id":"2505.17104","title":"P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark","created":"2025-05-21","cited_by_count":17,"area":null},{"id":"2603.26648","title":"Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification","created":"2026-03-27","cited_by_count":16,"area":"agents"},{"id":"2509.22644","title":"WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning","created":"2025-09-26","cited_by_count":15,"area":"lr"},{"id":"2511.08195","title":"UI2Code^N: UI-to-Code Generation as Interactive Visual Optimization","created":"2025-11-11","cited_by_count":15,"area":null},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2510.11498","title":"ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding","created":"2025-10-13","cited_by_count":14,"area":"mllm"},{"id":"2601.04203","title":"FronTalk: Benchmarking Front-End Development as Conversational Code Generation with Multi-Modal Feedback","created":"2025-12-05","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":"2509.22097","title":"SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios","created":"2025-09-26","cited_by_count":13,"area":"agents"},{"id":"2602.01576","title":"Generative Visual Code Mobile World Models","created":"2026-02-02","cited_by_count":13,"area":"wm"},{"id":"2509.24709","title":"IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?","created":"2025-09-29","cited_by_count":12,"area":null},{"id":"2605.17637","title":"WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games","created":"2026-05-17","cited_by_count":12,"area":"agents"},{"id":"2505.05283","title":"Software Development Life Cycle Perspective: A Survey of Benchmarks for Code Large Language Models and Agents","created":"2025-05-08","cited_by_count":11,"area":"agents"},{"id":"2603.25732","title":"BizGenEval: A Systematic Benchmark for Commercial Visual Content Generation","created":"2026-03-26","cited_by_count":11,"area":null},{"id":"2511.06251","title":"WebVIA: A Web-based Vision-Language Agentic Framework for Interactive and Verifiable UI-to-Code Generation","created":"2025-11-09","cited_by_count":10,"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":"2511.15567","title":"Computer-Use Agents as Judges for Generative User Interface","created":"2025-11-19","cited_by_count":9,"area":"agents"},{"id":"2512.19918","title":"Widget2Code: From Visual Widgets to UI Code via Multimodal LLMs","created":"2025-12-22","cited_by_count":9,"area":"mllm"},{"id":"2605.15677","title":"VCG-Bench: Towards A Unified Visual-Centric Benchmark for Structured Generation and Editing","created":"2026-05-15","cited_by_count":9,"area":"mllm"},{"id":"2606.01869","title":"WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis","created":"2026-06-01","cited_by_count":9,"area":null},{"id":"2608.13560","title":"AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design","created":"2026-08-13","cited_by_count":9,"area":"agents"},{"id":"2507.19492","title":"ChartGen: Scaling Chart Understanding Via Code-Guided Synthetic Chart Generation","created":"2025-05-31","cited_by_count":8,"area":null},{"id":"2603.27703","title":"KAT-Coder-V2 Technical Report","created":"2026-03-29","cited_by_count":8,"area":"agents"},{"id":"2601.19697","title":"AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2508.19227","title":"Generative Interfaces for Language Models","created":"2025-08-26","cited_by_count":6,"area":null},{"id":"2510.08697","title":"BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution","created":"2025-10-09","cited_by_count":6,"area":"alignment"},{"id":"2604.18224","title":"WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models","created":"2026-04-20","cited_by_count":6,"area":"agents"},{"id":"2509.12159","title":"EfficientUICoder: A Bidirectional Token Compression Framework for Efficient MLLM-Based UI Code Generation","created":"2025-09-15","cited_by_count":5,"area":"inference"},{"id":"2606.02915","title":"Any2Poster: Any-Source Poster Generation Across Modalities and Domains","created":"2026-06-01","cited_by_count":5,"area":null},{"id":"2502.18525","title":"Programming with Pixels: Can Computer-Use Agents do Software Engineering?","created":"2025-02-24","cited_by_count":4,"area":"agents"},{"id":"2503.19654","title":"RGB-Th-Bench: A Dense benchmark for Visual-Thermal Understanding of Vision Language Models","created":"2025-03-25","cited_by_count":4,"area":"mllm"},{"id":"2507.18625","title":"3D Software Synthesis Driven by Constraint-Expressive Intermediate Representation","created":"2025-07-24","cited_by_count":4,"area":null},{"id":"2510.09724","title":"InteractScience: Programmatic and Visually-Grounded Evaluation of Interactive Scientific Demonstration Code Generation","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2603.17508","title":"Omni-I2C: A Holistic Benchmark for High-Fidelity Image-to-Code Generation","created":"2026-03-18","cited_by_count":4,"area":"mllm"},{"id":"2603.25226","title":"WebTestBench: Evaluating Computer-Use Agents towards End-to-End Automated Web Testing","created":"2026-03-26","cited_by_count":4,"area":"agents"},{"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":"2606.05920","title":"Asuka-Bench: Benchmarking Code Agents on Underspecified User Intent and Multi-Round Refinement","created":"2026-06-04","cited_by_count":4,"area":"agents"},{"id":"2606.06538","title":"WorldBench: A Challenging and Visually Diverse Multimodal Reasoning Benchmark","created":"2026-06-04","cited_by_count":4,"area":"lr"},{"id":"2607.01883","title":"PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation","created":"2026-07-02","cited_by_count":4,"area":null},{"id":"2608.10408","title":"VisEditBench: Can Vision-Language Models Edit Visualization Code from Multimodal Feedback?","created":"2026-08-11","cited_by_count":4,"area":"mllm"},{"id":"2501.05122","title":"Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model","created":"2025-01-09","cited_by_count":3,"area":"mllm"},{"id":"2508.20410","title":"UI-Bench: A Benchmark for Evaluating Design Capabilities of AI Text-to-App Tools","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2510.03341","title":"OpusAnimation: Code-Based Dynamic Chart Generation","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2510.04097","title":"WebRenderBench: Enhancing Web Interface Generation through Layout-Style Consistency and Reinforcement Learning","created":"2025-10-05","cited_by_count":3,"area":null},{"id":"2601.20615","title":"DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoning","created":"2026-01-28","cited_by_count":3,"area":"rag"},{"id":"2603.10757","title":"CodePercept: Code-Grounded Visual STEM Perception for MLLMs","created":"2026-03-11","cited_by_count":3,"area":"lr"},{"id":"2603.22744","title":"LH-Bench: Skill-Grounded Evaluation of Long-Horizon Agents on Subjective Enterprise Tasks","created":"2026-03-24","cited_by_count":3,"area":"agents"},{"id":"2604.05839","title":"Vision-Guided Iterative Refinement for Frontend Code Generation","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2605.26144","title":"VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents","created":"2026-05-22","cited_by_count":3,"area":"agents"},{"id":"2605.30000","title":"Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2606.00750","title":"I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications","created":"2026-05-30","cited_by_count":3,"area":null},{"id":"2602.03798","title":"FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation","created":"2026-02-03","cited_by_count":2,"area":"agents"},{"id":"2604.22192","title":"CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution","created":"2026-04-24","cited_by_count":2,"area":"mllm"},{"id":"2605.08560","title":"ZAYA1-VL-8B Technical Report","created":"2026-05-08","cited_by_count":2,"area":"mllm"},{"id":"2605.12586","title":"3D Primitives are a Spatial Language for VLMs","created":"2026-05-12","cited_by_count":2,"area":"mllm"},{"id":"2605.25160","title":"ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis","created":"2026-05-24","cited_by_count":2,"area":"agents"},{"id":"2605.26807","title":"HTMLCure: Turning Browser Experience into State Guided Repair for Interactive HTML","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2606.01414","title":"Agent Skills Should Go Beyond Text: The Case for Visual Skills","created":"2026-05-31","cited_by_count":2,"area":null},{"id":"2607.02436","title":"Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study","created":"2026-07-02","cited_by_count":2,"area":"lr"},{"id":"2607.04610","title":"RoboVista: Evaluating Vision Language Models for Diverse Robot Applications","created":"2026-07-06","cited_by_count":2,"area":"mllm"},{"id":"2607.18859","title":"PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents","created":"2026-07-21","cited_by_count":2,"area":"lr"},{"id":"2608.24138","title":"Rubrics as Visual-Repair Context for Self-Evolving UI-to-Code Generation","created":"2026-08-25","cited_by_count":2,"area":"mllm"},{"id":"2510.15842","title":"Paper2Web: Let's Make Your Paper Alive!","created":"2025-10-17","cited_by_count":1,"area":null},{"id":"2601.06458","title":"PixRec: Leveraging Visual Context for Next-Item Prediction in Sequential Recommendation","created":"2026-01-10","cited_by_count":1,"area":null},{"id":"2602.07645","title":"From Dead Pixels to Editable Slides: Infographic Reconstruction into Native Google Slides via Vision-Language Region Understanding","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2602.12311","title":"Perceptual Self-Reflection in Agentic Physics Simulation Code Generation","created":"2026-02-12","cited_by_count":1,"area":"agents"},{"id":"2602.18548","title":"1D-Bench: A Benchmark for Iterative UI Code Generation with Visual Feedback in Real-World","created":"2026-02-20","cited_by_count":1,"area":null},{"id":"2603.14724","title":"GameUIAgent: An LLM-Powered Framework for Automated Game UI Design with Structured Intermediate Representation","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2603.25118","title":"AnyDoc: Enhancing Document Generation via Large-Scale HTML/CSS Data Synthesis and Height-Aware Reinforcement Optimization","created":"2026-03-26","cited_by_count":1,"area":"synth"},{"id":"2603.29301","title":"Self-Consistency for LLM-Based Motion Trajectory Generation and Verification","created":"2026-03-31","cited_by_count":1,"area":"lr"},{"id":"2604.07558","title":"Generative Experiences for Digital Mental Health Interventions: Evidence from a Randomized Study","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2604.19750","title":"Coding with Eyes: Visual Feedback Unlocks Reliable GUI Code Generating and Debugging","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2604.25220","title":"DATAREEL: Automated Data-Driven Video Story Generation with Animations","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2604.27419","title":"InteractWeb-Bench: Can Multimodal Agent Escape Blind Execution in Interactive Website Generation?","created":"2026-04-30","cited_by_count":1,"area":"agents"},{"id":"2605.19382","title":"PRISM: A Benchmark for Programmatic Spatial-Temporal Reasoning","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2606.00154","title":"Benchmarking Multimodal LLMs on Code Generation for Complex Interactive Webpages","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.10334","title":"Self-Distillation Policy Optimization via Visual Feedback: Bridging Code and Visual Artifacts","created":"2026-06-09","cited_by_count":1,"area":"distill"},{"id":"2606.16262","title":"UXBench: Measuring the Actionability of LLM-Generated UX Critiques","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2606.20711","title":"Video2Code: Generating Interactive Webpages from UI Videos via Action-Aware Revisit","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2606.31732","title":"UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization","created":"2026-06-30","cited_by_count":1,"area":"mllm"},{"id":"2607.04727","title":"Dashboard2Code: Evaluating Multimodal Models on Reconstructing Interactive Dashboards","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2607.23588","title":"JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents","created":"2026-07-26","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"}],"next_cursor":"100"}