{"total":73,"rows":[{"id":"2503.10677","title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","created":"2025-03-11","cited_by_count":36,"area":"rag"},{"id":"2509.25085","title":"jina-reranker-v3: Last but Not Late Interaction for Listwise Document Reranking","created":"2025-09-29","cited_by_count":24,"area":null},{"id":"2503.00353","title":"U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystack","created":"2025-03-01","cited_by_count":20,"area":"rag"},{"id":"2506.23115","title":"MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings","created":"2025-06-29","cited_by_count":20,"area":"mllm"},{"id":"2412.12559","title":"EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation","created":"2024-12-17","cited_by_count":17,"area":"rag"},{"id":"2507.00994","title":"Should We Still Pretrain Encoders with Masked Language Modeling?","created":"2025-07-01","cited_by_count":16,"area":null},{"id":"2504.19754","title":"Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation","created":"2025-04-28","cited_by_count":13,"area":"rag"},{"id":"2509.11552","title":"HiChunk: Evaluating and Enhancing Retrieval-Augmented Generation with Hierarchical Chunking","created":"2025-09-15","cited_by_count":12,"area":"rag"},{"id":"2510.06999","title":"Towards Reliable Retrieval in RAG Systems for Large Legal Datasets","created":"2025-10-08","cited_by_count":12,"area":"rag"},{"id":"2512.15649","title":"VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?","created":"2025-12-17","cited_by_count":11,"area":"mllm"},{"id":"2506.20821","title":"MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering","created":"2025-06-25","cited_by_count":9,"area":"rag"},{"id":"2602.11151","title":"Diffusion-Pretrained Dense and Contextual Embeddings","created":"2026-02-11","cited_by_count":9,"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":"2504.10529","title":"HeteRAG: A Heterogeneous Retrieval-augmented Generation Framework with Decoupled Knowledge Representations","created":"2025-04-12","cited_by_count":6,"area":"rag"},{"id":"2603.15685","title":"DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression","created":"2026-03-15","cited_by_count":6,"area":"inference"},{"id":"2501.14733","title":"LLM as HPC Expert: Extending RAG Architecture for HPC Data","created":"2024-12-09","cited_by_count":5,"area":null},{"id":"2603.18516","title":"Total Recall QA: A Verifiable Evaluation Suite for Deep Research Agents","created":"2026-03-19","cited_by_count":5,"area":"agents"},{"id":"2509.17395","title":"FinDebate: Multi-Agent Collaborative Intelligence for Financial Analysis","created":"2025-09-22","cited_by_count":4,"area":"rag"},{"id":"2504.05104","title":"AI for Climate Finance: Agentic Retrieval and Multi-Step Reasoning for Early Warning System Investments","created":"2025-04-07","cited_by_count":3,"area":"lr"},{"id":"2505.24715","title":"CoRet: Improved Retriever for Code Editing","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2601.07765","title":"Contrastive Learning with Narrative Twins for Modeling Story Salience","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2601.16934","title":"Information Representation Fairness in Long-Document Embeddings: The Peculiar Interaction of Positional and Language Bias","created":"2026-01-23","cited_by_count":2,"area":null},{"id":"2604.01733","title":"From BM25 to Corrective RAG: Benchmarking Retrieval Strategies for Text-and-Table Documents","created":"2026-04-02","cited_by_count":2,"area":"rag"},{"id":"2504.05106","title":"SpeakEasy: Enhancing Text-to-Speech Interactions for Expressive Content Creation","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2508.08545","title":"OmniLLP: Enhancing LLM-based Log Level Prediction with Context-Aware Retrieval","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2601.05265","title":"Cross-Document Topic-Aligned Chunking for Retrieval-Augmented Generation","created":"2025-11-08","cited_by_count":1,"area":"rag"},{"id":"2602.22225","title":"SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG","created":"2025-12-17","cited_by_count":1,"area":"rag"},{"id":"2603.07612","title":"KohakuRAG: A simple RAG framework with hierarchical document indexing","created":"2026-03-08","cited_by_count":1,"area":"rag"},{"id":"2603.22633","title":"Graph-Aware Late Chunking for Retrieval-Augmented Generation in Biomedical Literature","created":"2026-03-23","cited_by_count":1,"area":"rag"},{"id":"2603.25333","title":"Adaptive Chunking: Optimizing Chunking-Method Selection for RAG","created":"2026-03-26","cited_by_count":1,"area":"rag"},{"id":"2604.20849","title":"SPIRE: Structure-Preserving Interpretable Retrieval of Evidence","created":"2026-02-12","cited_by_count":1,"area":"rag"},{"id":"2604.24334","title":"Reducing Redundancy in Retrieval-Augmented Generation through Chunk Filtering","created":"2026-04-27","cited_by_count":1,"area":"rag"},{"id":"2606.00881","title":"Chunking Methods on Retrieval-Augmented Generation - Effectiveness Evaluation Against Computational Cost and Limitations","created":"2026-05-30","cited_by_count":1,"area":"rag"},{"id":"2607.01852","title":"Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts","created":"2026-07-02","cited_by_count":1,"area":"rag"},{"id":"2608.04330","title":"Right Reset: Chunking by Prefix Removal","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2609.33659","title":"Learning Multimodal Embeddings with Evidence-Aligned Readout","created":"2026-09-27","cited_by_count":1,"area":"mllm"},{"id":"2501.02772","title":"GeAR: Generation Augmented Retrieval","created":"2025-01-06","cited_by_count":0,"area":null},{"id":"2503.17952","title":"SLIDE: Sliding Localized Information for Document Extraction","created":"2025-03-23","cited_by_count":0,"area":null},{"id":"2510.13329","title":"Embedding-Based Context-Aware Reranker","created":"2025-10-15","cited_by_count":0,"area":"rag"},{"id":"2512.08802","title":"Democratizing ML for Enterprise Security: A Self-Sustained Attack Detection Framework","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2601.08851","title":"M\\'as contexto no es mejor. Paradoja de la diluci\\'on vectorial en RAG corporativos","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2601.09118","title":"LPCAN: Lightweight Pyramid Cross-Attention Network for Rail Surface Defect Detection Using RGB-D Data","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2601.09238","title":"Knowledge-Embedded and Hypernetwork-Guided Few-Shot Substation Meter Defect Image Generation Method","created":"2026-01-14","cited_by_count":0,"area":"diffusion"},{"id":"2601.09730","title":"Clinical Document Metadata Extraction: A Scoping Review","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2601.20881","title":"MA-LipNet: Multi-Dimensional Attention Networks for Robust Lipreading","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.12278","title":"AttentionRetriever: Attention Layers are Secretly Long Document Retrievers","created":"2026-02-12","cited_by_count":0,"area":"rag"},{"id":"2602.13361","title":"The Diffusion Duet: Harmonizing Dual Channels with Wavelet Suppression for Image Separation","created":"2026-02-13","cited_by_count":0,"area":"diffusion"},{"id":"2602.15903","title":"Detecting Deepfakes with Multivariate Soft Blending and CLIP-based Image-Text Alignment","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2603.00118","title":"Efficient Image Super-Resolution with Multi-Scale Spatial Adaptive Attention Networks","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2603.13429","title":"A Deformable Attention-Based Detection Transformer with Cross-Scale Feature Fusion for Industrial Coil Spring Inspection","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.18409","title":"TopoChunker: Topology-Aware Agentic Document Chunking Framework","created":"2026-03-19","cited_by_count":0,"area":"rag"},{"id":"2603.23533","title":"MDKeyChunker: Single-Call LLM Enrichment with Rolling Keys and Key-Based Restructuring for High-Accuracy RAG","created":"2026-03-08","cited_by_count":0,"area":"rag"},{"id":"2604.17677","title":"Semantic Entanglement in Vector-Based Retrieval: A Formal Framework and Context-Conditioned Disentanglement Pipeline for Agentic RAG Systems","created":"2026-04-20","cited_by_count":0,"area":"rag"},{"id":"2605.10296","title":"Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.22203","title":"Evaluation of Chunking Strategies for Effective Text Embedding in Low-Resource Language on Agricultural Documents","created":"2026-05-21","cited_by_count":0,"area":"rag"},{"id":"2605.22247","title":"IdioLink: Retrieving Meaning Beyond Words Across Idiomatic and Literal Expressions","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.00884","title":"Context-aware tokenization for Cross-subject Emotion Decoding from EEG","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.01240","title":"Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving Chunking","created":"2026-05-31","cited_by_count":0,"area":"lr"},{"id":"2606.06906","title":"EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.18381","title":"SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG","created":"2026-06-16","cited_by_count":0,"area":"rag"},{"id":"2606.18781","title":"Lost in a Single Vector: Improving Long-Document Retrieval with Chunk Evidence Aggregation","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2607.05927","title":"CMDR: Contextual Multimodal Document Retrieval","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.18603","title":"AutoIndex: Learning Representation Programs for Retrieval","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.18660","title":"Computational Measurement of Team-Process Phase Dynamics in Collaborative Virtual Reality","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.21610","title":"Semantic Compression Trees: Multi-Resolution Knowledge Retrieval via Hierarchical Semantic Residuals","created":"2026-08-21","cited_by_count":0,"area":"rag"},{"id":"2608.26949","title":"A Table Is Worth 64 Tokens: Pixel-level Compression for Multi-Table Document Question Answering","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2608.31139","title":"Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation","created":"2026-08-31","cited_by_count":0,"area":"rag"},{"id":"2609.02275","title":"Do Large Language Models Capture the Diversity in their Training Data?","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.33075","title":"QureRadEmbed: Structuring Radiological Similarity through Attribute and Reasoning Supervision","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.07091","title":"Smart Content Ingestion for Generative AI Workloads","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.10170","title":"Does Document Structure Help Dense Retrieval? A Placebo-Controlled Ablation of Four Mechanisms Across Two Corpora","created":"2026-10-07","cited_by_count":0,"area":"rag"},{"id":"2610.12243","title":"NativeScope: Relation-Localized Retrieval over Native Topology with a Correct Anchor","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.13277","title":"Beyond the Final Embedding: Retrieving Memories from Token-Level Evidence","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}