{"total":112,"rows":[{"id":"2503.08026","title":"In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents","created":"2025-03-11","cited_by_count":106,"area":"agents"},{"id":"2505.12540","title":"Harnessing the Universal Geometry of Embeddings","created":"2025-05-18","cited_by_count":55,"area":null},{"id":"2503.05061","title":"No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding","created":"2025-03-07","cited_by_count":54,"area":null},{"id":"2504.10478","title":"Weight Ensembling Improves Reasoning in Language Models","created":"2025-04-14","cited_by_count":38,"area":"lr"},{"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,"area":null},{"id":"2502.07972","title":"Training Sparse Mixture Of Experts Text Embedding Models","created":"2025-02-11","cited_by_count":32,"area":"moe"},{"id":"2506.09944","title":"Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking","created":"2025-06-11","cited_by_count":31,"area":"lr"},{"id":"2510.09719","title":"ICL-Router: In-Context Learned Model Representations for LLM Routing","created":"2025-10-10","cited_by_count":28,"area":null},{"id":"2510.04905","title":"Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches","created":"2025-10-06","cited_by_count":23,"area":"rag"},{"id":"2602.15547","title":"jina-embeddings-v5-text: Task-Targeted Embedding Distillation","created":"2026-02-17","cited_by_count":22,"area":null},{"id":"2503.07018","title":"Toward Multi-Session Personalized Conversation: A Large-Scale Dataset and Hierarchical Tree Framework for Implicit Reasoning","created":"2025-03-10","cited_by_count":21,"area":"lr"},{"id":"2412.20953","title":"GASLITEing the Retrieval: Exploring Vulnerabilities in Dense Embedding-based Search","created":"2024-12-30","cited_by_count":20,"area":"rag"},{"id":"2502.18460","title":"DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers","created":"2025-02-25","cited_by_count":19,"area":null},{"id":"2505.11545","title":"TARGET: Benchmarking Table Retrieval for Generative Tasks","created":"2025-05-14","cited_by_count":17,"area":null},{"id":"2507.20804","title":"MMGraphRAG: Bridging Vision and Language with Interpretable Multimodal Knowledge Graphs","created":"2025-07-28","cited_by_count":16,"area":null},{"id":"2510.03458","title":"Omni-Embed-Nemotron: A Unified Multimodal Retrieval Model for Text, Image, Audio, and Video","created":"2025-10-03","cited_by_count":16,"area":null},{"id":"2510.08252","title":"ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval","created":"2025-10-09","cited_by_count":16,"area":null},{"id":"2504.13128","title":"FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2505.10740","title":"SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval","created":"2025-05-15","cited_by_count":11,"area":null},{"id":"2506.08354","title":"Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning","created":"2025-06-10","cited_by_count":10,"area":null},{"id":"2507.05633","title":"SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression","created":"2025-07-08","cited_by_count":10,"area":"rag"},{"id":"2505.14136","title":"Local Mixtures of Experts: Essentially Free Test-Time Training via Model Merging","created":"2025-05-20","cited_by_count":9,"area":"moe"},{"id":"2506.23601","title":"Semantic-guided Diverse Decoding for Large Language Model","created":"2025-06-30","cited_by_count":9,"area":null},{"id":"2511.01268","title":"Rescuing the Unpoisoned: Efficient Defense against Knowledge Corruption Attacks on RAG Systems","created":"2025-11-03","cited_by_count":9,"area":"rag"},{"id":"2603.01425","title":"LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval","created":"2026-03-02","cited_by_count":9,"area":"lr"},{"id":"2506.00789","title":"RARE: Retrieval-Aware Robustness Evaluation for Retrieval-Augmented Generation Systems","created":"2025-06-01","cited_by_count":8,"area":"rag"},{"id":"2506.01890","title":"CogniAlign: Word-Level Multimodal Speech Alignment with Gated Cross-Attention for Alzheimer's Detection","created":"2025-06-02","cited_by_count":7,"area":null},{"id":"2510.10062","title":"HUME: Measuring the Human-Model Performance Gap in Text Embedding Tasks","created":"2025-10-11","cited_by_count":7,"area":null},{"id":"2501.11960","title":"TAD-Bench: A Comprehensive Benchmark for Embedding-Based Text Anomaly Detection","created":"2025-01-21","cited_by_count":6,"area":null},{"id":"2506.08553","title":"From Pixels to Graphs: using Scene and Knowledge Graphs for HD-EPIC VQA Challenge","created":"2025-06-10","cited_by_count":6,"area":null},{"id":"2508.01680","title":"T-GRAG: A Dynamic GraphRAG Framework for Resolving Temporal Conflicts and Redundancy in Knowledge Retrieval","created":"2025-08-03","cited_by_count":6,"area":"rag"},{"id":"2602.05735","title":"CSRv2: Unlocking Ultra-Sparse Embeddings","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2505.10989","title":"DRAGON: Domain-specific Robust Automatic Data Generation for RAG Optimization","created":"2025-05-16","cited_by_count":5,"area":"rag"},{"id":"2507.08983","title":"Exploiting Leaderboards for Large-Scale Distribution of Malicious Models","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2508.17858","title":"LexSemBridge: Fine-Grained Dense Representation Enhancement through Token-Aware Embedding Augmentation","created":"2025-08-25","cited_by_count":5,"area":"rag"},{"id":"2511.02770","title":"Beyond Single Embeddings: Capturing Diverse Targets with Multi-Query Retrieval","created":"2025-11-04","cited_by_count":5,"area":null},{"id":"2508.06059","title":"Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System","created":"2025-08-08","cited_by_count":4,"area":"agents"},{"id":"2510.02348","title":"mini-vec2vec: Scaling Universal Geometry Alignment with Linear Transformations","created":"2025-09-27","cited_by_count":4,"area":null},{"id":"2511.16326","title":"ARK: Answer-Centric Retriever Tuning via KG-augmented Curriculum Learning","created":"2025-11-20","cited_by_count":4,"area":"rag"},{"id":"2501.13288","title":"Task-Oriented Automatic Fact-Checking with Frame-Semantics","created":"2025-01-23","cited_by_count":3,"area":null},{"id":"2504.08930","title":"VectorLiteRAG: Latency-Aware and Fine-Grained Resource Partitioning for Efficient RAG","created":"2025-04-11","cited_by_count":3,"area":"rag"},{"id":"2505.12925","title":"CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2508.21632","title":"QZhou-Embedding Technical Report","created":"2025-08-29","cited_by_count":3,"area":null},{"id":"2601.12369","title":"Can Deep Research Agents Retrieve and Organize? Evaluating the Synthesis Gap with Expert Taxonomies","created":"2026-01-18","cited_by_count":3,"area":"agents"},{"id":"2602.20094","title":"CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching","created":"2026-02-23","cited_by_count":3,"area":"lr"},{"id":"2604.05821","title":"CLEAR: Cross-Lingual Enhancement in Alignment via Reverse-training","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2606.08457","title":"The Consistency Illusion: How Multi-Agent Debate Hides Reasoning Misalignment","created":"2026-06-07","cited_by_count":3,"area":"lr"},{"id":"2503.00674","title":"OrdRankBen: A Novel Ranking Benchmark for Ordinal Relevance in NLP","created":"2025-03-02","cited_by_count":2,"area":null},{"id":"2504.03814","title":"Recursive Training Loops in LLMs: How training data properties modulate distribution shift in generated data?","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2507.05006","title":"Do We Really Need Specialization? Evaluating Generalist Text Embeddings for Zero-Shot Recommendation and Search","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2507.06419","title":"Teach a Reward Model to Correct Itself: Reward Guided Adversarial Failure Discovery for Robust Reward Modeling","created":"2025-07-08","cited_by_count":2,"area":"alignment"},{"id":"2507.21989","title":"Benchmarking Filtered Approximate Nearest Neighbor Search Algorithms on Transformer-based Embedding Vectors","created":"2025-07-29","cited_by_count":2,"area":"rag"},{"id":"2508.20912","title":"Research Challenges in Relational Database Management Systems for LLM Queries","created":"2025-08-28","cited_by_count":2,"area":null},{"id":"2512.21582","title":"LLM-Free Image Captioning Evaluation in Reference-Flexible Settings","created":"2025-12-25","cited_by_count":2,"area":null},{"id":"2602.22175","title":"DySCO: Dynamic Attention-Scaling Decoding for Long-Context Language Models","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2503.10886","title":"Taxonomic Reasoning for Rare Arthropods: Combining Dense Image Captioning and RAG for Interpretable Classification","created":"2025-03-13","cited_by_count":1,"area":"rag"},{"id":"2504.04572","title":"Multimodal Lengthy Videos Retrieval Framework and Evaluation Metric","created":"2025-04-06","cited_by_count":1,"area":null},{"id":"2505.11557","title":"AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2505.12660","title":"Predicting Reaction Time to Comprehend Scenes with Foveated Scene Understanding Maps","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2505.22157","title":"LASER: Stratified Selective Sampling for Instruction Tuning with Dedicated Scoring Strategy","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.00425","title":"Inter-Passage Verification for Multi-evidence Multi-answer QA","created":"2025-05-31","cited_by_count":1,"area":"rag"},{"id":"2506.01992","title":"No Free Lunch in Active Learning: LLM Embedding Quality Dictates Query Strategy Success","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2506.14235","title":"A Multi-Expert Structural-Semantic Hybrid Framework for Unveiling Historical Patterns in Temporal Knowledge Graphs","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2507.09090","title":"DS@GT at Touch\\'e: Large Language Models for Retrieval-Augmented Debate","created":"2025-07-12","cited_by_count":1,"area":"rag"},{"id":"2508.10899","title":"A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2508.16936","title":"THEME: Enhancing Thematic Investing with Semantic Stock Representations and Temporal Dynamics","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2508.20244","title":"Do Students Rely on AI? Analysis of Student-ChatGPT Conversations from a Field Study","created":"2025-08-27","cited_by_count":1,"area":null},{"id":"2508.20750","title":"Specializing General-purpose LLM Embeddings for Implicit Hate Speech Detection across Datasets","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2509.16248","title":"GraphMend: Code Transformations for Fixing Graph Breaks in PyTorch 2","created":"2025-09-17","cited_by_count":1,"area":null},{"id":"2510.01801","title":"Detecting LLM-Generated Spam Reviews by Integrating Language Model Embeddings and Graph Neural Network","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2510.18454","title":"Engagement Undermines Safety: How Stereotypes and Toxicity Shape Humor in Language Models","created":"2025-10-21","cited_by_count":1,"area":"safety"},{"id":"2602.12783","title":"SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2603.04532","title":"Still Fresh? Evaluating Temporal Drift in Retrieval Benchmarks","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2603.07146","title":"Fine-Grained Table Retrieval Through the Lens of Complex Queries","created":"2026-03-07","cited_by_count":1,"area":null},{"id":"2603.19415","title":"Scalable Prompt Routing via Fine-Grained Latent Task Discovery","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2605.27345","title":"MATCHA: Matching Text via Contrastive Semantic Alignment","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2605.28190","title":"The Harder Text Embedding Benchmark (HTEB): Beyond One-dimensional Static Robustness","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2607.17879","title":"Exploratory and Assimilating Reflection: Reflective Recall Cycle for Long-term Memory","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2607.27506","title":"Models for minimalist RAG: B1ade 335M Embedding and 1B Parameter Small Language Models","created":"2026-07-29","cited_by_count":1,"area":"rag"},{"id":"2608.25986","title":"Multi-Granularity Context-Enhanced RAG over Multimodal Knowledge Graphs","created":"2026-08-26","cited_by_count":1,"area":"mllm"},{"id":"2503.13859","title":"Less is More: Improving Motion Diffusion Models with Sparse Keyframes","created":"2025-03-18","cited_by_count":0,"area":"diffusion"},{"id":"2506.12637","title":"How Grounded is Wikipedia? A Study on Structured Evidential Support and Retrieval","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2506.15246","title":"TopClustRAG at SIGIR 2025 LiveRAG Challenge","created":"2025-06-18","cited_by_count":0,"area":"rag"},{"id":"2507.03329","title":"NDAI-NeuroMAP: A Neuroscience-Specific Embedding Model for Domain-Specific Retrieval","created":"2025-07-04","cited_by_count":0,"area":null},{"id":"2507.07847","title":"From Ambiguity to Accuracy: The Transformative Effect of Coreference Resolution on Retrieval-Augmented Generation systems","created":"2025-07-10","cited_by_count":0,"area":"rag"},{"id":"2509.14622","title":"Adversarial Distilled Retrieval-Augmented Guarding Model for Online Malicious Intent Detection","created":"2025-09-18","cited_by_count":0,"area":"rag"},{"id":"2510.01178","title":"COM-BOM: Bayesian Exemplar Search for Efficiently Exploring the Accuracy-Calibration Pareto Frontier","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2510.02938","title":"Finding Diamonds in Conversation Haystacks: A Benchmark for Conversational Data Retrieval","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2510.09293","title":"One Sentence, Two Embeddings: Contrastive Learning of Explicit and Implicit Semantic Representations","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2603.04741","title":"CONE: Embeddings for Complex Numerical Data Preserving Unit and Variable Semantics","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.05446","title":"NaiLIA: Multimodal Nail Design Retrieval Based on Dense Intent Descriptions and Palette Queries","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.06176","title":"Robustness Risk of Conversational Retrieval: Identifying and Mitigating Noise Sensitivity in Qwen3-Embedding Model","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2604.09541","title":"Trans-RAG: Query-Centric Vector Transformation for Secure Cross-Organizational Retrieval","created":"2026-04-10","cited_by_count":0,"area":"rag"},{"id":"2604.16301","title":"Domain-Specific Query Understanding for Automotive Applications: A Modular and Scalable Approach","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2605.13047","title":"Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency","created":"2026-05-13","cited_by_count":0,"area":"mllm"},{"id":"2605.17823","title":"Why We Look Where We Look: Emergent Human-like Fixations of a Foveated Visual Language Model Maximizing Scene Understanding","created":"2026-05-18","cited_by_count":0,"area":"mllm"},{"id":"2605.20729","title":"MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks","created":"2026-05-20","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":"2606.00590","title":"Critic-R: Improving Agentic Search using Instruction-tuned Retrievers with Natural Language Introspective Feedback","created":"2026-05-30","cited_by_count":0,"area":"agents"},{"id":"2606.21851","title":"TALAS: Teacher-Anchored Layer Alignment with Adaptive Sharpness-Aware Minimization for Embedding Distillation","created":"2026-06-20","cited_by_count":0,"area":"distill"}],"next_cursor":"100"}