{"list":"other","total":56,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2404.16130","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","created":"2024-04-24","cited_by_count":1453},{"id":"2310.06839","title":"LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression","created":"2023-10-10","cited_by_count":453},{"id":"2303.04048","title":"Is ChatGPT a Good NLG Evaluator? A Preliminary Study","created":"2023-03-07","cited_by_count":422},{"id":"2309.15217","title":"Ragas: Automated Evaluation of Retrieval Augmented Generation","created":"2023-09-26","cited_by_count":418},{"id":"2505.07062","title":"Seed1.5-VL Technical Report","created":"2025-05-11","cited_by_count":373},{"id":"2410.05779","title":"LightRAG: Simple and Fast Retrieval-Augmented Generation","created":"2024-10-08","cited_by_count":315},{"id":"2404.02060","title":"Long-context LLMs Struggle with Long In-context Learning","created":"2024-04-02","cited_by_count":286},{"id":"2303.14968","title":"Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective","created":"2023-03-27","cited_by_count":280},{"id":"2410.21819","title":"Self-Preference Bias in LLM-as-a-Judge","created":"2024-10-29","cited_by_count":258},{"id":"2501.00321","title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","created":"2024-12-31","cited_by_count":173},{"id":"2311.11810","title":"DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding","created":"2023-11-20","cited_by_count":106},{"id":"2405.11985","title":"MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering","created":"2024-05-20","cited_by_count":93},{"id":"2408.04187","title":"Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation","created":"2024-08-08","cited_by_count":90},{"id":"2412.20367","title":"Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey","created":"2024-12-29","cited_by_count":83},{"id":"2505.14059","title":"Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting","created":"2025-05-20","cited_by_count":79},{"id":"2308.11592","title":"UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding","created":"2023-08-19","cited_by_count":74},{"id":"2409.04701","title":"Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models","created":"2024-09-07","cited_by_count":73},{"id":"2406.01326","title":"TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy","created":"2024-06-03","cited_by_count":71},{"id":"2301.01635","title":"SPTS v2: Single-Point Scene Text Spotting","created":"2023-01-04","cited_by_count":66},{"id":"2203.15221","title":"Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection","created":"2022-03-29","cited_by_count":65},{"id":"2412.12974","title":"Attentive Eraser: Unleashing Diffusion Model's Object Removal Potential via Self-Attention Redirection Guidance","created":"2024-12-17","cited_by_count":63},{"id":"2404.12803","title":"TextSquare: Scaling up Text-Centric Visual Instruction Tuning","created":"2024-04-19","cited_by_count":62},{"id":"2407.01976","title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding","created":"2024-07-02","cited_by_count":57},{"id":"2407.16364","title":"Harmonizing Visual Text Comprehension and Generation","created":"2024-07-23","cited_by_count":54},{"id":"2311.13120","title":"Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer","created":"2023-11-22","cited_by_count":53},{"id":"2305.04676","title":"Enhancing Knowledge Graph Construction Using Large Language Models","created":"2023-05-08","cited_by_count":44},{"id":"2408.12928","title":"ParGo: Bridging Vision-Language with Partial and Global Views","created":"2024-08-23","cited_by_count":40},{"id":"2503.20680","title":"Vision as LoRA","created":"2025-03-26","cited_by_count":37},{"id":"2505.15154","title":"Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning","created":"2025-05-21","cited_by_count":35},{"id":"2408.11857","title":"Hermes 3 Technical Report","created":"2024-08-15","cited_by_count":34},{"id":"2207.11934","title":"Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning","created":"2022-07-25","cited_by_count":33},{"id":"2410.11538","title":"MCTBench: Multimodal Cognition towards Text-Rich Visual Scenes Benchmark","created":"2024-10-15","cited_by_count":26},{"id":"2505.11015","title":"WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild?","created":"2025-05-16","cited_by_count":26},{"id":"2505.13077","title":"Advancing Sequential Numerical Prediction in Autoregressive Models","created":"2025-05-19","cited_by_count":26},{"id":"2505.22521","title":"Evaluating Supervised Learning Models for Fraud Detection: A Comparative Study of Classical and Deep Architectures on Imbalanced Transaction Data","created":"2025-05-28","cited_by_count":20},{"id":"2505.19369","title":"SETransformer: A Hybrid Attention-Based Architecture for Robust Human Activity Recognition","created":"2025-05-25","cited_by_count":19},{"id":"2509.09731","title":"Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning","created":"2025-09-10","cited_by_count":19},{"id":"2512.23333","title":"CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation","created":"2025-12-29","cited_by_count":19},{"id":"2411.03707","title":"Fine-Tuning Vision-Language Model for Automated Engineering Drawing Information Extraction","created":"2024-11-06","cited_by_count":18},{"id":"2511.22850","title":"Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding","created":"2025-11-28","cited_by_count":18},{"id":"2305.14579","title":"Real-Time Idling Vehicles Detection using Combined Audio-Visual Deep Learning","created":"2023-05-23","cited_by_count":17},{"id":"2305.13582","title":"Translation and Fusion Improves Zero-shot Cross-lingual Information Extraction","created":"2023-05-23","cited_by_count":15},{"id":"2506.00107","title":"Gated Multimodal Graph Learning for Personalized Recommendation","created":"2025-05-30","cited_by_count":15},{"id":"2409.03708","title":"RAG based Question-Answering for Contextual Response Prediction System","created":"2024-09-05","cited_by_count":14},{"id":"2410.21170","title":"Joint Audio-Visual Idling Vehicle Detection with Streamlined Input Dependencies","created":"2024-10-28","cited_by_count":14},{"id":"2508.09670","title":"MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement","created":"2025-08-13","cited_by_count":14},{"id":"2408.08535","title":"CommunityKG-RAG: Leveraging Community Structures in Knowledge Graphs for Advanced Retrieval-Augmented Generation in Fact-Checking","created":"2024-08-16","cited_by_count":11},{"id":"2406.11162","title":"How Good are LLMs at Relation Extraction under Low-Resource Scenario? Comprehensive Evaluation","created":"2024-06-17","cited_by_count":9}],"next_cursor":null}