{"total":76,"rows":[{"id":"2510.11693","title":"Scaling Language-Centric Omnimodal Representation Learning","created":"2025-10-13","cited_by_count":22,"area":"mllm"},{"id":"2602.15547","title":"jina-embeddings-v5-text: Task-Targeted Embedding Distillation","created":"2026-02-17","cited_by_count":22,"area":null},{"id":"2509.23883","title":"DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning","created":"2025-09-28","cited_by_count":20,"area":null},{"id":"2603.01050","title":"MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baseline","created":"2026-03-01","cited_by_count":20,"area":"agents"},{"id":"2508.21290","title":"Efficient Code Embeddings from Code Generation Models","created":"2025-08-29","cited_by_count":13,"area":null},{"id":"2510.05038","title":"Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization","created":"2025-10-06","cited_by_count":12,"area":null},{"id":"2510.09733","title":"VisRAG2.0: Mitigating Visual Hallucinations via Evidence-Guided Multi-Image Reasoning in Visual Retrieval-Augmented Generation","created":"2025-10-10","cited_by_count":10,"area":"lr"},{"id":"2602.03992","title":"Nemotron ColEmbed V2: Top-Performing Late Interaction Embedding Models for Visual Document Retrieval","created":"2026-02-03","cited_by_count":10,"area":"rag"},{"id":"2602.19549","title":"Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework","created":"2026-02-23","cited_by_count":10,"area":null},{"id":"2602.21202","title":"Multi-Vector Index Compression in Any Modality","created":"2026-02-24","cited_by_count":10,"area":null},{"id":"2602.19961","title":"Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2604.10167","title":"Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval","created":"2026-04-11","cited_by_count":8,"area":null},{"id":"2601.21262","title":"CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding","created":"2026-01-29","cited_by_count":7,"area":"mllm"},{"id":"2603.12572","title":"LMEB: Long-horizon Memory Embedding Benchmark","created":"2026-03-13","cited_by_count":7,"area":null},{"id":"2606.11864","title":"CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Coding","created":"2026-06-10","cited_by_count":7,"area":"agents"},{"id":"2512.21616","title":"TAMEing Long Contexts in Personalization: Towards Training-Free and State-Aware MLLM Personalized Assistant","created":"2025-12-25","cited_by_count":6,"area":"mllm"},{"id":"2601.20107","title":"Structural Anchor Pruning: Training-Free Multi-Vector Compression for Visual Document Retrieval","created":"2026-01-27","cited_by_count":6,"area":"mllm"},{"id":"2508.03644","title":"Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?","created":"2025-08-05","cited_by_count":5,"area":"mllm"},{"id":"2511.16654","title":"Comparison of Text-Based and Image-Based Retrieval in Multimodal Retrieval Augmented Generation Large Language Model Systems","created":"2025-11-20","cited_by_count":5,"area":"rag"},{"id":"2601.07125","title":"ReinPool: Reinforcement Learning Pooling Multi-Vector Embeddings for Retrieval System","created":"2026-01-12","cited_by_count":5,"area":"lr"},{"id":"2602.13758","title":"OmniScience: A Large-scale Multi-modal Dataset for Scientific Image Understanding","created":"2026-02-14","cited_by_count":5,"area":"mllm"},{"id":"2603.01666","title":"Beyond the Grid: Layout-Informed Multi-Vector Retrieval with Parsed Visual Document Representations","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2604.10741","title":"Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generation","created":"2026-04-12","cited_by_count":4,"area":"agents"},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2512.03514","title":"M3DR: Towards Universal Multilingual Multimodal Document Retrieval","created":"2025-12-03","cited_by_count":3,"area":null},{"id":"2603.20366","title":"WebNavigator: Global Web Navigation via Interaction Graph Retrieval","created":"2026-03-20","cited_by_count":3,"area":null},{"id":"2608.21494","title":"Retrieval Needs Multivectors: An Exponential Separation","created":"2026-08-21","cited_by_count":3,"area":null},{"id":"2608.23646","title":"MolEmb: Multimodal Large Language Models Can Be Strong Molecular Embedding Models","created":"2026-08-24","cited_by_count":3,"area":"mllm"},{"id":"2601.03262","title":"Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Survey","created":"2025-12-16","cited_by_count":2,"area":"rag"},{"id":"2602.08254","title":"SynthAgent: A Multi-Agent LLM Framework for Realistic Patient Simulation -- A Case Study in Obesity with Mental Health Comorbidities","created":"2026-02-09","cited_by_count":2,"area":"agents"},{"id":"2602.17687","title":"IRPAPERS: A Visual Document Benchmark for Scientific Retrieval and Question Answering","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2605.06460","title":"MINER: Mining Multimodal Internal Representation for Efficient Retrieval","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2606.07654","title":"MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matryoshka Training Framework","created":"2026-06-03","cited_by_count":2,"area":"mllm"},{"id":"2607.15205","title":"MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization","created":"2026-07-16","cited_by_count":2,"area":null},{"id":"2608.29607","title":"SnapBench: Benchmarking Snap-and-Ask Multimodal Retrieval for Mobile Interactions","created":"2026-08-30","cited_by_count":2,"area":null},{"id":"2508.12778","title":"HeteroRAG: A Heterogeneous Retrieval-Augmented Generation Framework for Medical Vision Language Tasks","created":"2025-08-18","cited_by_count":1,"area":"mllm"},{"id":"2512.04847","title":"Language Models as Semantic Teachers: Post-Training Alignment for Medical Audio Understanding","created":"2025-12-04","cited_by_count":1,"area":null},{"id":"2512.10393","title":"Cross-modal Retrieval Models for Stripped Binary Analysis","created":"2025-12-11","cited_by_count":1,"area":null},{"id":"2601.21853","title":"LEMUR: Learned Multi-Vector Retrieval","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2602.08342","title":"UrbanGraphEmbeddings: Learning and Evaluating Spatially Grounded Multimodal Embeddings for Urban Science","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2603.04852","title":"Non-Parametric Structural Priors for Geometry Theorem Prediction","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.13349","title":"MURE: Hierarchical Multi-Resolution Encoding via Vision-Language Models for Visual Document Retrieval","created":"2026-03-07","cited_by_count":1,"area":"mllm"},{"id":"2604.18508","title":"Document-as-Image Representations Fall Short for Scientific Retrieval","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2604.19047","title":"RARE: Redundancy-Aware Retrieval Evaluation Framework for High-Similarity Corpora","created":"2026-04-21","cited_by_count":1,"area":"rag"},{"id":"2605.29507","title":"Xetrieval: Mechanistically Explaining Dense Retrieval","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.23539","title":"LightSTAR: Efficient Visual Document Retrieval via Lightweight Selection with Vision-Adaptive Refinement","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2608.01794","title":"Illuminating Visual Identity in Universal Multimodal Embeddings","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2609.07561","title":"EigenLI: Spectral Approximations to Late Interaction","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2510.15946","title":"Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrieval","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2510.20381","title":"VLSP 2025 MLQA-TSR Challenge: Vietnamese Multimodal Legal Question Answering on Traffic Sign Regulation","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2510.26861","title":"Evaluating Perspectival Biases in Cross-Modal Retrieval","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2512.07100","title":"Dual Refinement Cycle Learning: Unsupervised Text Classification of Mamba and Community Detection on Text Attributed Graph","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2602.13961","title":"MarsRetrieval: Benchmarking Vision-Language Models for Planetary-Scale Geospatial Retrieval on Mars","created":"2026-02-15","cited_by_count":0,"area":"mllm"},{"id":"2602.22678","title":"ViCLIP-OT: The First Foundation Vision-Language Model for Vietnamese Image-Text Retrieval with Optimal Transport","created":"2026-02-26","cited_by_count":0,"area":"mllm"},{"id":"2603.16455","title":"Evo-Retriever: LLM-Guided Curriculum Evolution with Viewpoint-Pathway Collaboration for Multimodal Document Retrieval","created":"2026-03-17","cited_by_count":0,"area":"mllm"},{"id":"2603.17186","title":"Visual Product Search Benchmark","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.12081","title":"Human-Inspired Context-Selective Multimodal Memory for Social Robots","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.18434","title":"TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.30917","title":"Inference-Free Multimodal Learned Sparse Retrieval for Production-Scale Visual Document Search","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.04591","title":"Fine-grained Fragment Retrieval in Multi-modal Long-form Dialogues","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.13647","title":"SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.20643","title":"SPARC: A Multi-Agent System for Electrical Circuit Question Answering","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2606.29068","title":"A Comparative Study on Affective Cues in Text Embeddings Across Psychological Emotion Theories","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2607.16208","title":"ColGraphRAG: Late-Interaction Evidence Retrieval for Multimodal GraphRAG","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2607.24165","title":"Do Current Retrievers Cover All the Evidence? A Controlled Study of Conjunctive Cross-Page Retrieval","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.01211","title":"VaRS-Doc: Interpretation-Aware Variant Representations via Latent Self-Probing for Visual Document Retrieval","created":"2026-08-02","cited_by_count":0,"area":"rag"},{"id":"2608.01389","title":"KoVRE: Training an Efficient Embedding Model for Korean Visual Document Retrieval","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.15698","title":"ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval","created":"2026-08-16","cited_by_count":0,"area":"rag"},{"id":"2608.20840","title":"KoViDoRe: A Benchmark for Korean Visual Document Retrieval","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.30163","title":"Doc-REFRAG: Rethinking Multimodal Document Retrieval-Augmented Generation","created":"2026-08-31","cited_by_count":0,"area":"rag"},{"id":"2609.11460","title":"ReGround: Grounding Reviewer Comments in Multimodal Evidence","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.21018","title":"MAGIC: Marginal-Guided Compression with Optimal Transport for Efficient Visual Document Retrieval","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.14196","title":"Simple Linear Corrections for Compression in Late Interaction","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14531","title":"LongHisDoc: A Comprehensive Benchmark for Chinese Long Historical Document Understanding","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.17057","title":"VL-DocIR: A Benchmark for Vision-Based Long Document Information Retrieval","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.20367","title":"Cascaded Retrieval with Cross-Modal Query Refinement for Efficient Visual Document Search","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}