{"list":"other","total":180,"rows":[{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"2004.12832","title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","created":"2020-04-27","cited_by_count":1178},{"id":"2504.21776","title":"WebThinker: Empowering Large Reasoning Models with Deep Research Capability","created":"2025-04-30","cited_by_count":335},{"id":"2501.09136","title":"Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG","created":"2025-01-15","cited_by_count":249},{"id":"2410.10594","title":"VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents","created":"2024-10-14","cited_by_count":245},{"id":"2601.04720","title":"Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking","created":"2026-01-08","cited_by_count":230},{"id":"2410.05160","title":"VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks","created":"2024-10-07","cited_by_count":228},{"id":"2402.17193","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","created":"2024-02-27","cited_by_count":204},{"id":"2412.16855","title":"GME: Improving Universal Multimodal Retrieval by Multimodal LLMs","created":"2024-12-22","cited_by_count":170},{"id":"2311.17136","title":"UniIR: Training and Benchmarking Universal Multimodal Information Retrievers","created":"2023-11-28","cited_by_count":166},{"id":"2411.02571","title":"MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs","created":"2024-11-04","cited_by_count":161},{"id":"2407.12883","title":"BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval","created":"2024-07-16","cited_by_count":158},{"id":"2503.17547","title":"Learning Multi-Level Features with Matryoshka Sparse Autoencoders","created":"2025-03-21","cited_by_count":143},{"id":"2212.02623","title":"Unifying Vision, Text, and Layout for Universal Document Processing","created":"2022-12-05","cited_by_count":140},{"id":"2509.20354","title":"EmbeddingGemma: Powerful and Lightweight Text Representations","created":"2025-09-24","cited_by_count":139},{"id":"2209.06640","title":"Revisiting Neural Scaling Laws in Language and Vision","created":"2022-09-13","cited_by_count":132},{"id":"2502.13595","title":"MMTEB: Massive Multilingual Text Embedding Benchmark","created":"2025-02-19","cited_by_count":125},{"id":"2411.04952","title":"M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding","created":"2024-11-07","cited_by_count":111},{"id":"2406.11251","title":"Unifying Multimodal Retrieval via Document Screenshot Embedding","created":"2024-06-17","cited_by_count":110},{"id":"2405.11273","title":"Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts","created":"2024-05-18","cited_by_count":108},{"id":"2412.01720","title":"LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant","created":"2024-12-02","cited_by_count":106},{"id":"2406.13629","title":"InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales","created":"2024-06-19","cited_by_count":101},{"id":"2406.14497","title":"CodeRAG-Bench: Can Retrieval Augment Code Generation?","created":"2024-06-20","cited_by_count":91},{"id":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","cited_by_count":85},{"id":"2412.14475","title":"MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval","created":"2024-12-19","cited_by_count":84},{"id":"2207.11871","title":"Towards Complex Document Understanding By Discrete Reasoning","created":"2022-07-25","cited_by_count":82},{"id":"2506.18902","title":"jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval","created":"2025-06-23","cited_by_count":76},{"id":"2504.17432","title":"Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs","created":"2025-04-24","cited_by_count":73},{"id":"2407.13193","title":"Retrieval-Augmented Generation for Natural Language Processing: A Survey","created":"2024-07-18","cited_by_count":71},{"id":"2510.21618","title":"DeepAgent: A General Reasoning Agent with Scalable Toolsets","created":"2025-10-24","cited_by_count":71},{"id":"2502.18418","title":"Rank1: Test-Time Compute for Reranking in Information Retrieval","created":"2025-02-25","cited_by_count":70},{"id":"2403.15246","title":"FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions","created":"2024-03-22","cited_by_count":69},{"id":"2505.22019","title":"VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning","created":"2025-05-28","cited_by_count":68},{"id":"2509.13309","title":"WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents","created":"2025-09-16","cited_by_count":68},{"id":"2406.04292","title":"VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval","created":"2024-06-06","cited_by_count":67},{"id":"2503.13964","title":"MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding","created":"2025-03-18","cited_by_count":67},{"id":"2502.18017","title":"ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents","created":"2025-02-25","cited_by_count":66},{"id":"2508.12752","title":"Deep Research: A Survey of Autonomous Research Agents","created":"2025-08-18","cited_by_count":66},{"id":"2111.08609","title":"Document AI: Benchmarks, Models and Applications","created":"2021-11-16","cited_by_count":62},{"id":"2505.17166","title":"ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval","created":"2025-05-22","cited_by_count":61},{"id":"2407.02883","title":"CoIR: A Comprehensive Benchmark for Code Information Retrieval Models","created":"2024-07-03","cited_by_count":60},{"id":"2504.09795","title":"VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents","created":"2025-04-14","cited_by_count":59},{"id":"2407.13766","title":"Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmark","created":"2024-07-18","cited_by_count":55},{"id":"2412.11936","title":"A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges","created":"2024-12-16","cited_by_count":55},{"id":"2503.04812","title":"LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning","created":"2025-03-04","cited_by_count":55},{"id":"2403.12027","title":"From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models","created":"2024-03-18","cited_by_count":53},{"id":"2407.21439","title":"MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Training","created":"2024-07-31","cited_by_count":50},{"id":"2502.08468","title":"mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data","created":"2025-02-12","cited_by_count":49},{"id":"2406.18219","title":"A Closer Look into Mixture-of-Experts in Large Language Models","created":"2024-06-26","cited_by_count":48},{"id":"2312.06420","title":"Localization Is All You Evaluate: Data Leakage in Online Mapping Datasets and How to Fix It","created":"2023-12-11","cited_by_count":44},{"id":"2501.08828","title":"MMDocIR: Benchmarking Multimodal Retrieval for Long Documents","created":"2025-01-15","cited_by_count":43},{"id":"2402.08327","title":"PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers","created":"2024-02-13","cited_by_count":42},{"id":"2507.09477","title":"Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs","created":"2025-07-13","cited_by_count":42},{"id":"2510.13515","title":"UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning","created":"2025-10-15","cited_by_count":42},{"id":"2412.10704","title":"VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation","created":"2024-12-14","cited_by_count":41},{"id":"2509.18095","title":"MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction","created":"2025-09-22","cited_by_count":39},{"id":"2511.00405","title":"UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings","created":"2025-11-01","cited_by_count":38},{"id":"2410.10814","title":"Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free","created":"2024-10-14","cited_by_count":37},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37},{"id":"2508.07995","title":"DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval","created":"2025-08-11","cited_by_count":37},{"id":"2404.06347","title":"RAR-b: Reasoning as Retrieval Benchmark","created":"2024-04-09","cited_by_count":36},{"id":"2505.16470","title":"Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering","created":"2025-05-22","cited_by_count":36},{"id":"2506.20923","title":"KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model","created":"2025-06-26","cited_by_count":36},{"id":"2502.12342","title":"REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark","created":"2025-02-17","cited_by_count":35},{"id":"2502.02871","title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","created":"2025-02-05","cited_by_count":33},{"id":"2011.13534","title":"A Survey of Deep Learning Approaches for OCR and Document Understanding","created":"2020-11-27","cited_by_count":32},{"id":"2401.17671","title":"Contextual Feature Extraction Hierarchies Converge in Large Language Models and the Brain","created":"2024-01-31","cited_by_count":32},{"id":"2412.12591","title":"LLMs are Also Effective Embedding Models: An In-depth Overview","created":"2024-12-17","cited_by_count":32},{"id":"2503.18016","title":"Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlook","created":"2025-03-23","cited_by_count":32},{"id":"2503.19900","title":"CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning","created":"2025-03-25","cited_by_count":31},{"id":"2402.19014","title":"Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models","created":"2024-02-29","cited_by_count":30},{"id":"2508.04183","title":"Characterizing Deep Research: A Benchmark and Formal Definition","created":"2025-08-06","cited_by_count":30},{"id":"2505.14432","title":"Rank-K: Test-Time Reasoning for Listwise Reranking","created":"2025-05-20","cited_by_count":29},{"id":"2510.27350","title":"RzenEmbed: Towards Comprehensive Multimodal Retrieval","created":"2025-10-31","cited_by_count":29},{"id":"2412.08746","title":"DocVLM: Make Your VLM an Efficient Reader","created":"2024-12-11","cited_by_count":28},{"id":"2505.11293","title":"Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining","created":"2025-05-16","cited_by_count":28},{"id":"2402.09642","title":"Answer is All You Need: Instruction-following Text Embedding via Answering the Question","created":"2024-02-15","cited_by_count":27},{"id":"2505.18405","title":"RaDeR: Reasoning-aware Dense Retrieval Models","created":"2025-05-23","cited_by_count":27},{"id":"2507.05513","title":"Llama Nemoretriever Colembed: Top-Performing Text-Image Retrieval Model","created":"2025-07-07","cited_by_count":27},{"id":"2503.01776","title":"Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation","created":"2025-03-03","cited_by_count":26},{"id":"2506.04997","title":"Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings","created":"2025-06-05","cited_by_count":26},{"id":"2408.16672","title":"Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever","created":"2024-08-29","cited_by_count":25},{"id":"2508.12800","title":"Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward","created":"2025-08-18","cited_by_count":25},{"id":"1706.06064","title":"Recent Advance in Content-based Image Retrieval: A Literature Survey","created":"2017-06-19","cited_by_count":24},{"id":"2503.18132","title":"MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection","created":"2025-03-23","cited_by_count":24},{"id":"2602.13823","title":"Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings","created":"2026-02-14","cited_by_count":24},{"id":"2408.15045","title":"DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding","created":"2024-08-27","cited_by_count":23},{"id":"2411.04434","title":"Scaling Laws for Pre-training Agents and World Models","created":"2024-11-07","cited_by_count":23},{"id":"2504.03151","title":"Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)","created":"2025-04-04","cited_by_count":23},{"id":"2506.02020","title":"Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying","created":"2025-05-28","cited_by_count":23},{"id":"2503.18071","title":"Mind with Eyes: from Language Reasoning to Multimodal Reasoning","created":"2025-03-23","cited_by_count":22},{"id":"2505.14558","title":"R2MED: A Benchmark for Reasoning-Driven Medical Retrieval","created":"2025-05-20","cited_by_count":22},{"id":"2510.11693","title":"Scaling Language-Centric Omnimodal Representation Learning","created":"2025-10-13","cited_by_count":22},{"id":"2408.01287","title":"Deep Learning based Visually Rich Document Content Understanding: A Survey","created":"2024-08-02","cited_by_count":21},{"id":"2506.02454","title":"Multimodal DeepResearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Framework","created":"2025-06-03","cited_by_count":21},{"id":"2506.12364","title":"MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval","created":"2025-06-14","cited_by_count":21},{"id":"2510.01149","title":"ModernVBERT: Towards Smaller Visual Document Retrievers","created":"2025-10-01","cited_by_count":21},{"id":"2510.03663","title":"UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG","created":"2025-10-04","cited_by_count":21},{"id":"2511.12609","title":"Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data","created":"2025-11-16","cited_by_count":21}],"next_cursor":"100"}