{"list":"other","total":67,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"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":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658},{"id":"2401.09670","title":"DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving","created":"2024-01-18","cited_by_count":617},{"id":"1912.13318","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","created":"2019-12-31","cited_by_count":553},{"id":"2402.19173","title":"StarCoder 2 and The Stack v2: The Next Generation","created":"2024-02-29","cited_by_count":502},{"id":"2009.10297","title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","created":"2020-09-22","cited_by_count":479},{"id":"2507.01006","title":"GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning","created":"2025-07-01","cited_by_count":466},{"id":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366},{"id":"2203.03850","title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","created":"2022-03-08","cited_by_count":361},{"id":"2406.11931","title":"DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence","created":"2024-06-17","cited_by_count":331},{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300},{"id":"2308.13418","title":"Nougat: Neural Optical Understanding for Academic Documents","created":"2023-08-25","cited_by_count":245},{"id":"2403.12895","title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding","created":"2024-03-19","cited_by_count":220},{"id":"1904.01906","title":"What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis","created":"2019-04-03","cited_by_count":191},{"id":"2310.03533","title":"Large Language Models for Software Engineering: Survey and Open Problems","created":"2023-10-05","cited_by_count":181},{"id":"2409.01704","title":"General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model","created":"2024-09-03","cited_by_count":180},{"id":"2404.05719","title":"Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs","created":"2024-04-08","cited_by_count":176},{"id":"1412.1842","title":"Reading Text in the Wild with Convolutional Neural Networks","created":"2014-12-04","cited_by_count":122},{"id":"2401.00908","title":"DocLLM: A layout-aware generative language model for multimodal document understanding","created":"2023-12-31","cited_by_count":116},{"id":"1807.01544","title":"TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes","created":"2018-07-04","cited_by_count":114},{"id":"2306.14893","title":"LongCoder: A Long-Range Pre-trained Language Model for Code Completion","created":"2023-06-26","cited_by_count":112},{"id":"1809.08799","title":"Chargrid: Towards Understanding 2D Documents","created":"2018-09-24","cited_by_count":100},{"id":"2402.04615","title":"ScreenAI: A Vision-Language Model for UI and Infographics Understanding","created":"2024-02-07","cited_by_count":98},{"id":"2507.23361","title":"SWE-Exp: Experience-Driven Software Issue Resolution","created":"2025-07-31","cited_by_count":65},{"id":"2108.11590","title":"AVATAR: A Parallel Corpus for Java-Python Program Translation","created":"2021-08-26","cited_by_count":59},{"id":"2507.23348","title":"SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution","created":"2025-07-31","cited_by_count":53},{"id":"2406.11612","title":"Long Code Arena: a Set of Benchmarks for Long-Context Code Models","created":"2024-06-17","cited_by_count":50},{"id":"2303.03004","title":"xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval","created":"2023-03-06","cited_by_count":47},{"id":"2601.16746","title":"SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents","created":"2026-01-23","cited_by_count":44},{"id":"2406.10819","title":"GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding","created":"2024-06-16","cited_by_count":43},{"id":"2510.00446","title":"LongCodeZip: Compress Long Context for Code Language Models","created":"2025-10-01","cited_by_count":39},{"id":"2509.14635","title":"SWE-QA: Can Language Models Answer Repository-level Code Questions?","created":"2025-09-18","cited_by_count":38},{"id":"2505.07897","title":"LongCodeBench: Evaluating Coding LLMs at 1M Context Windows","created":"2025-05-12","cited_by_count":37},{"id":"2508.05988","title":"Pruning the Unsurprising: Efficient LLM Reasoning via First-Token Surprisal","created":"2025-08-08","cited_by_count":32},{"id":"2401.06461","title":"Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human Programmers","created":"2024-01-12","cited_by_count":27},{"id":"2206.14390","title":"Diet Code Is Healthy: Simplifying Programs for Pre-trained Models of Code","created":"2022-06-29","cited_by_count":24},{"id":"2410.07400","title":"Advocating Character Error Rate for Multilingual ASR Evaluation","created":"2024-10-09","cited_by_count":24},{"id":"2508.04295","title":"EvoC2Rust: A Skeleton-guided Framework for Project-Level C-to-Rust Translation","created":"2025-08-06","cited_by_count":19},{"id":"2410.12468","title":"Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios","created":"2024-10-16","cited_by_count":18},{"id":"2601.00376","title":"In Line with Context: Repository-Level Code Generation via Context Inlining","created":"2026-01-01","cited_by_count":18},{"id":"2512.02924","title":"AutoNeural: Co-Designing Vision-Language Models for NPU Inference","created":"2025-12-02","cited_by_count":17},{"id":"2601.05110","title":"GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts","created":"2026-01-08","cited_by_count":17},{"id":"2503.12374","title":"Beyond Final Code: A Process-Oriented Error Analysis of Software Development Agents in Real-World GitHub Scenarios","created":"2025-03-16","cited_by_count":14},{"id":"2506.21614","title":"LastingBench: Defend Benchmarks Against Knowledge Leakage","created":"2025-06-21","cited_by_count":14},{"id":"2601.11255","title":"Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering","created":"2026-01-16","cited_by_count":14},{"id":"2508.13666","title":"The Hidden Cost of Readability: How Code Formatting Silently Consumes Your LLM Budget","created":"2025-08-19","cited_by_count":12},{"id":"2308.13963","title":"GPTCloneBench: A comprehensive benchmark of semantic clones and cross-language clones using GPT-3 model and SemanticCloneBench","created":"2023-08-26","cited_by_count":11},{"id":"2512.15649","title":"VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?","created":"2025-12-17","cited_by_count":11},{"id":"2404.16333","title":"AI Coders Are Among Us: Rethinking Programming Language Grammar Towards Efficient Code Generation","created":"2024-04-25","cited_by_count":10},{"id":"2405.11196","title":"Natural Is The Best: Model-Agnostic Code Simplification for Pre-trained Large Language Models","created":"2024-05-18","cited_by_count":10},{"id":"2507.09019","title":"On Evaluating Performance of LLM Inference Serving Systems","created":"2025-07-11","cited_by_count":10},{"id":"2508.20212","title":"FlowMalTrans: Unsupervised Binary Code Translation for Malware Detection Using Flow-Adapter Architecture","created":"2025-08-27","cited_by_count":10},{"id":"2508.15709","title":"Position Bias Mitigates Position Bias:Mitigate Position Bias Through Inter-Position Knowledge Distillation","created":"2025-08-21","cited_by_count":9},{"id":"2601.03714","title":"Visual Merit or Linguistic Crutch? A Close Look at DeepSeek-OCR","created":"2026-01-07","cited_by_count":8},{"id":"2505.21003","title":"Uncertainty Unveiled: Can Exposure to More In-context Examples Mitigate Uncertainty for Large Language Models?","created":"2025-05-27","cited_by_count":5},{"id":"2511.16546","title":"Progressive Supernet Training for Efficient Visual Autoregressive Modeling","created":"2025-11-20","cited_by_count":5},{"id":"2512.08266","title":"Token Sugar: Making Source Code Sweeter for LLMs through Token-Efficient Shorthand","created":"2025-12-09","cited_by_count":4},{"id":"2601.05485","title":"Readability-Robust Code Summarization via Meta Curriculum Learning","created":"2026-01-09","cited_by_count":4},{"id":"1911.01702","title":"DocParser: Hierarchical Structure Parsing of Document Renderings","created":"2019-11-05","cited_by_count":2}],"next_cursor":null}