{"list":"other","total":51,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2403.20330","title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","created":"2024-03-29","cited_by_count":914},{"id":"2512.02556","title":"DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models","created":"2025-12-02","cited_by_count":815},{"id":"1603.07396","title":"A Diagram Is Worth A Dozen Images","created":"2016-03-24","cited_by_count":804},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2306.10012","title":"MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing","created":"2023-06-16","cited_by_count":624},{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567},{"id":"2409.02813","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","created":"2024-09-04","cited_by_count":512},{"id":"2402.19173","title":"StarCoder 2 and The Stack v2: The Next Generation","created":"2024-02-29","cited_by_count":502},{"id":"1710.07300","title":"FigureQA: An Annotated Figure Dataset for Visual Reasoning","created":"2017-10-19","cited_by_count":319},{"id":"2306.09265","title":"LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models","created":"2023-06-15","cited_by_count":217},{"id":"2007.11301","title":"DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation","created":"2020-07-22","cited_by_count":159},{"id":"2401.03601","title":"InFoBench: Evaluating Instruction Following Ability in Large Language Models","created":"2024-01-07","cited_by_count":135},{"id":"2102.02798","title":"Im2Vec: Synthesizing Vector Graphics without Vector Supervision","created":"2021-02-04","cited_by_count":116},{"id":"1705.07962","title":"pix2code: Generating Code from a Graphical User Interface Screenshot","created":"2017-05-22","cited_by_count":114},{"id":"2211.11319","title":"VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models","created":"2022-11-21","cited_by_count":112},{"id":"2304.14400","title":"IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers","created":"2023-04-27","cited_by_count":75},{"id":"2502.00299","title":"ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference","created":"2025-02-01","cited_by_count":60},{"id":"2404.09486","title":"MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems","created":"2024-04-15","cited_by_count":40},{"id":"2601.09668","title":"STEP3-VL-10B Technical Report","created":"2026-01-14","cited_by_count":32},{"id":"2411.11916","title":"From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing","created":"2024-11-18","cited_by_count":31},{"id":"2410.04199","title":"LongGenBench: Long-context Generation Benchmark","created":"2024-10-05","cited_by_count":28},{"id":"2404.13710","title":"SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities","created":"2024-04-21","cited_by_count":26},{"id":"2406.11033","title":"HAIChart: Human and AI Paired Visualization System","created":"2024-06-16","cited_by_count":26},{"id":"1910.08930","title":"Sketch2Code: Transformation of Sketches to UI in Real-time Using Deep Neural Network","created":"2019-10-20","cited_by_count":23},{"id":"2510.05091","title":"Factuality Matters: When Image Generation and Editing Meet Structured Visuals","created":"2025-10-06","cited_by_count":20},{"id":"2505.19433","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","created":"2025-05-26","cited_by_count":16},{"id":"2510.22373","title":"VisJudge-Bench: Aesthetics and Quality Assessment of Visualizations","created":"2025-10-25","cited_by_count":16},{"id":"2511.02778","title":"VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation","created":"2025-11-04","cited_by_count":16},{"id":"2504.09479","title":"Draw with Thought: Unleashing Multimodal Reasoning for Scientific Diagram Generation","created":"2025-04-13","cited_by_count":14},{"id":"2511.00010","title":"PlotCraft: Pushing the Limits of LLMs for Complex and Interactive Data Visualization","created":"2025-10-15","cited_by_count":14},{"id":"2502.19453","title":"SVGEditBench V2: A Benchmark for Instruction-based SVG Editing","created":"2025-02-26","cited_by_count":11},{"id":"2506.02073","title":"Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability","created":"2025-06-02","cited_by_count":8},{"id":"2603.28068","title":"AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation","created":"2026-03-30","cited_by_count":4}],"next_cursor":null}