{"list":"other","total":51,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"2204.08387","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","created":"2022-04-18","cited_by_count":485},{"id":"2310.17631","title":"JudgeLM: Fine-tuned Large Language Models are Scalable Judges","created":"2023-10-26","cited_by_count":367},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"2309.15402","title":"Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future","created":"2023-09-27","cited_by_count":184},{"id":"2405.11403","title":"MapCoder: Multi-Agent Code Generation for Competitive Problem Solving","created":"2024-05-18","cited_by_count":177},{"id":"2310.05470","title":"Generative Judge for Evaluating Alignment","created":"2023-10-09","cited_by_count":169},{"id":"2006.01038","title":"DocBank: A Benchmark Dataset for Document Layout Analysis","created":"2020-06-01","cited_by_count":153},{"id":"2403.03163","title":"Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering","created":"2024-03-05","cited_by_count":152},{"id":"2403.09029","title":"Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset","created":"2024-03-14","cited_by_count":129},{"id":"2402.03578","title":"LLM Multi-Agent Systems: Challenges and Open Problems","created":"2024-02-05","cited_by_count":120},{"id":"2410.12628","title":"DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception","created":"2024-10-16","cited_by_count":82},{"id":"2406.20098","title":"Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs","created":"2024-06-28","cited_by_count":74},{"id":"2407.00993","title":"Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents","created":"2024-07-01","cited_by_count":56},{"id":"2308.16890","title":"TouchStone: Evaluating Vision-Language Models by Language Models","created":"2023-08-31","cited_by_count":55},{"id":"2311.06495","title":"LayoutPrompter: Awaken the Design Ability of Large Language Models","created":"2023-11-11","cited_by_count":48},{"id":"2401.07037","title":"xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning","created":"2024-01-13","cited_by_count":46},{"id":"2404.06369","title":"WebCode2M: A Real-World Dataset for Code Generation from Webpage Designs","created":"2024-04-09","cited_by_count":44},{"id":"2111.02086","title":"Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task","created":"2021-11-03","cited_by_count":34},{"id":"2410.16232","title":"Sketch2Code: Evaluating Vision-Language Models for Interactive Web Design Prototyping","created":"2024-10-21","cited_by_count":29},{"id":"2406.16386","title":"Automatically Generating UI Code from Screenshot: A Divide-and-Conquer-Based Approach","created":"2024-06-24","cited_by_count":24},{"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},{"id":"2412.05210","title":"Evaluating and Aligning CodeLLMs on Human Preference","created":"2024-12-06","cited_by_count":22},{"id":"2501.15134","title":"BitsAI-CR: Automated Code Review via LLM in Practice","created":"2025-01-25","cited_by_count":22},{"id":"2505.09904","title":"UICopilot: Automating UI Synthesis via Hierarchical Code Generation from Webpage Designs","created":"2025-05-15","cited_by_count":22},{"id":"2412.11990","title":"ExecRepoBench: Multi-level Executable Code Completion Evaluation","created":"2024-12-16","cited_by_count":20},{"id":"2409.11667","title":"Bridging Design and Development with Automated Declarative UI Code Generation","created":"2024-09-18","cited_by_count":19},{"id":"1702.06228","title":"Learning to Generate Posters of Scientific Papers by Probabilistic Graphical Models","created":"2017-02-21","cited_by_count":18},{"id":"2406.16441","title":"UniCoder: Scaling Code Large Language Model via Universal Code","created":"2024-06-24","cited_by_count":18},{"id":"2407.19787","title":"SciPostLayout: A Dataset for Layout Analysis and Layout Generation of Scientific Posters","created":"2024-07-29","cited_by_count":14},{"id":"2405.04975","title":"Prototype2Code: End-to-end Front-end Code Generation from UI Design Prototypes","created":"2024-05-08","cited_by_count":10},{"id":"2502.17540","title":"PosterSum: A Multimodal Benchmark for Scientific Poster Summarization","created":"2025-02-24","cited_by_count":10},{"id":"2112.08550","title":"Neural Content Extraction for Poster Generation of Scientific Papers","created":"2021-12-16","cited_by_count":9},{"id":"2402.04867","title":"Multimodal Query Suggestion with Multi-Agent Reinforcement Learning from Human Feedback","created":"2024-02-07","cited_by_count":9},{"id":"1604.01219","title":"Learning to Generate Posters of Scientific Papers","created":"2016-04-05","cited_by_count":8},{"id":"2502.07487","title":"Multi-Agent Collaboration for Multilingual Code Instruction Tuning","created":"2025-02-11","cited_by_count":6},{"id":"2401.10110","title":"SVIPTR: Fast and Efficient Scene Text Recognition with Vision Permutable Extractor","created":"2024-01-18","cited_by_count":5},{"id":"2405.17336","title":"XFormParser: A Simple and Effective Multimodal Multilingual Semi-structured Form Parser","created":"2024-05-27","cited_by_count":5},{"id":"2405.20213","title":"PostDoc: Generating Poster from a Long Multimodal Document Using Deep Submodular Optimization","created":"2024-05-30","cited_by_count":5},{"id":"2410.18362","title":"WAFFLE: Finetuning Multi-Modal Models for Automated Front-End Development","created":"2024-10-24","cited_by_count":5}],"next_cursor":null}