{"total":89,"rows":[{"id":"2504.17343","title":"TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos","created":"2025-04-24","cited_by_count":97,"area":null},{"id":"2502.15603","title":"Do Multilingual LLMs Think In English?","created":"2025-02-21","cited_by_count":78,"area":"lr"},{"id":"2406.12094","title":"Who's asking? User personas and the mechanics of latent misalignment","created":"2024-06-17","cited_by_count":40,"area":"safety"},{"id":"2404.11553","title":"Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages","created":"2024-04-17","cited_by_count":38,"area":null},{"id":"2410.20482","title":"What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration","created":"2024-10-27","cited_by_count":31,"area":"lr"},{"id":"2409.13724","title":"Logically Consistent Language Models via Neuro-Symbolic Integration","created":"2024-09-09","cited_by_count":30,"area":null},{"id":"2410.17055","title":"Optimal Design for Reward Modeling in RLHF","created":"2024-10-22","cited_by_count":25,"area":"alignment"},{"id":"2503.08723","title":"Is CLIP ideal? No. Can we fix it? Yes!","created":"2025-03-10","cited_by_count":21,"area":null},{"id":"2407.12873","title":"Evaluation of RAG Metrics for Question Answering in the Telecom Domain","created":"2024-07-15","cited_by_count":20,"area":"rag"},{"id":"2406.01607","title":"Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmark","created":"2024-05-27","cited_by_count":19,"area":null},{"id":"2504.16318","title":"Semantics at an Angle: When Cosine Similarity Works Until It Doesn't","created":"2025-04-22","cited_by_count":13,"area":null},{"id":"2407.12813","title":"Data Generation Using Large Language Models for Text Classification: An Empirical Case Study","created":"2024-06-27","cited_by_count":11,"area":null},{"id":"2406.16535","title":"Token-based Decision Criteria Are Suboptimal in In-context Learning","created":"2024-06-24","cited_by_count":9,"area":null},{"id":"2412.02205","title":"DataLab: A Unified Platform for LLM-Powered Business Intelligence","created":"2024-12-03","cited_by_count":8,"area":null},{"id":"2405.18202","title":"IM-Context: In-Context Learning for Imbalanced Regression Tasks","created":"2024-05-28","cited_by_count":7,"area":null},{"id":"2511.17908","title":"Principled Context Engineering for RAG: Statistical Guarantees via Conformal Prediction","created":"2025-11-22","cited_by_count":6,"area":"rag"},{"id":"2406.10984","title":"Revisiting Cosine Similarity via Normalized ICA-transformed Embeddings","created":"2024-06-16","cited_by_count":5,"area":null},{"id":"2409.01466","title":"Enhancing LLM-Based Text Classification in Political Science: Automatic Prompt Optimization and Dynamic Exemplar Selection for Few-Shot Learning","created":"2024-09-02","cited_by_count":5,"area":null},{"id":"2505.00951","title":"Preserving Privacy and Utility in LLM-Based Product Recommendations","created":"2025-05-02","cited_by_count":5,"area":null},{"id":"2508.20282","title":"Network-Level Prompt and Trait Leakage in Local Research Agents","created":"2025-08-27","cited_by_count":5,"area":"agents"},{"id":"2406.00638","title":"COS-Mix: Cosine Similarity and Distance Fusion for Improved Information Retrieval","created":"2024-06-02","cited_by_count":4,"area":"rag"},{"id":"2412.15241","title":"Quantifying Positional Biases in Text Embedding Models","created":"2024-12-13","cited_by_count":4,"area":null},{"id":"2501.04444","title":"A novel Facial Recognition technique with Focusing on Masked Faces","created":"2025-01-08","cited_by_count":4,"area":null},{"id":"2506.22621","title":"Modeling Hierarchical Spaces: A Review and Unified Framework for Surrogate-Based Architecture Design","created":"2025-06-27","cited_by_count":4,"area":null},{"id":"2512.06404","title":"GENIUS: An Agentic AI Framework for Autonomous Design and Execution of Simulation Protocols","created":"2025-12-06","cited_by_count":4,"area":"agents"},{"id":"2409.15763","title":"IRSC: A Zero-shot Evaluation Benchmark for Information Retrieval through Semantic Comprehension in Retrieval-Augmented Generation Scenarios","created":"2024-09-24","cited_by_count":3,"area":"rag"},{"id":"2410.00260","title":"DoPAMine: Domain-specific Pre-training Adaptation from seed-guided data Mining","created":"2024-09-30","cited_by_count":3,"area":null},{"id":"2502.09340","title":"This looks like what? Challenges and Future Research Directions for Part-Prototype Models","created":"2025-02-13","cited_by_count":3,"area":null},{"id":"2504.12143","title":"ARCeR: an Agentic RAG for the Automated Definition of Cyber Ranges","created":"2025-04-16","cited_by_count":3,"area":"agents"},{"id":"2504.17902","title":"TRACE: Textual Relevance Augmentation and Contextual Encoding for Multimodal Hate Detection","created":"2025-04-24","cited_by_count":3,"area":null},{"id":"2510.06640","title":"Contextual Representation Flow Across Depth in State-Space and Transformer Architectures","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2506.05538","title":"SocialDF: Benchmark Dataset and Detection Model for Mitigating Harmful Deepfake Content on Social Media Platforms","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2507.05282","title":"Exploring LLM Capabilities in Extracting DCAT-Compatible Metadata for Data Cataloging","created":"2025-07-04","cited_by_count":2,"area":null},{"id":"2509.18156","title":"Event Causality Identification with Synthetic Control","created":"2025-09-16","cited_by_count":2,"area":null},{"id":"2509.23089","title":"Demystifying Network Foundation Models","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2606.23019","title":"ScalingAttention: Discovering Intrinsic Sparse Attention Topology for Video Diffusion Transformers","created":"2026-06-22","cited_by_count":2,"area":"diffusion"},{"id":"2409.19097","title":"Implementing NLPs in industrial process modeling: Addressing Categorical Variables","created":"2024-09-27","cited_by_count":1,"area":null},{"id":"2410.05233","title":"SimO Loss: Anchor-Free Contrastive Loss for Fine-Grained Supervised Contrastive Learning","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2501.16393","title":"Improving Network Threat Detection by Knowledge Graph, Large Language Model, and Imbalanced Learning","created":"2025-01-26","cited_by_count":1,"area":null},{"id":"2502.18291","title":"Neural Network Graph Similarity Computation Based on Graph Fusion","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2508.09021","title":"Attacks and Defenses Against LLM Fingerprinting","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2509.06401","title":"Do LLMs exhibit the same commonsense capabilities across languages?","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2509.09714","title":"How Small Transformation Expose the Weakness of Semantic Similarity Measures","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2509.16632","title":"DA-Font: Few-Shot Font Generation via Dual-Attention Hybrid Integration","created":"2025-09-20","cited_by_count":1,"area":null},{"id":"2509.17457","title":"Explainable AI for Analyzing Person-Specific Patterns in Facial Recognition Tasks","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2511.09814","title":"Multiple Treatments Causal Effects Estimation with Task Embeddings and Balanced Representation Learning","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2602.05266","title":"Beyond Cosine Similarity","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2603.06774","title":"Gauge Freedom and Metric Dependence in Neural Representation Spaces","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2603.23821","title":"Perturbation: A simple and efficient adversarial tracer for representation learning in language models","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2603.29488","title":"What Cosine Similarity of Label Representations Can and Cannot Tell us","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2604.02259","title":"Retrieval-Augmented Question Answering over Scientific Literature for the Electron-Ion Collider","created":"2026-04-02","cited_by_count":1,"area":"rag"},{"id":"2605.30040","title":"Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model Usage","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2608.01816","title":"Divergent large language model predictions from convergent representations in ambiguous word pairs","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2404.01356","title":"Perturbation Effects on Robustness and Individual Fairness","created":"2024-04-01","cited_by_count":0,"area":null},{"id":"2405.16213","title":"Learning Visual-Semantic Subspace Representations","created":"2024-05-25","cited_by_count":0,"area":null},{"id":"2406.07990","title":"Topological quantification of ambiguity in semantic search","created":"2024-06-12","cited_by_count":0,"area":null},{"id":"2407.16289","title":"Federated Learning for Face Recognition via Intra-subject Self-supervised Learning","created":"2024-07-23","cited_by_count":0,"area":null},{"id":"2410.12292","title":"How much do contextualized representations encode long-range context?","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2411.06264","title":"GuidelineGuard: An Agentic Framework for Medical Note Evaluation with Guideline Adherence","created":"2024-11-09","cited_by_count":0,"area":"agents"},{"id":"2501.11301","title":"Question-to-Question Retrieval for Hallucination-Free Knowledge Access: An Approach for Wikipedia and Wikidata Question Answering","created":"2025-01-20","cited_by_count":0,"area":null},{"id":"2502.09057","title":"Vision-Language In-Context Learning Driven Few-Shot Visual Inspection Model","created":"2025-02-13","cited_by_count":0,"area":"mllm"},{"id":"2502.18608","title":"Breaking Distortion-free Watermarks in Large Language Models","created":"2025-02-25","cited_by_count":0,"area":"safety"},{"id":"2503.16486","title":"Accodemy: AI Powered Code Learning Platform to Assist Novice Programmers in Overcoming the Fear of Coding","created":"2025-03-09","cited_by_count":0,"area":null},{"id":"2507.11751","title":"Survey of Genetic and Differential Evolutionary Algorithm Approaches to Search Documents Based On Semantic Similarity","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2507.11787","title":"Survey of Swarm Intelligence Approaches to Search Documents Based On Semantic Similarity","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2509.11982","title":"Examining the Relationship between Scientific Publishing Activity and Hype-Driven Financial Bubbles: A Comparison of the Dot-Com and AI Eras","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2511.05535","title":"Future of AI Models: A Computational perspective on Model collapse","created":"2025-10-29","cited_by_count":0,"area":"diffusion"},{"id":"2601.17705","title":"Distance-to-Distance Ratio: A Similarity Measure for Sentences Based on Rate of Change in LLM Embeddings","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2602.01922","title":"Embedding Learning on Multiplex Networks for Link Prediction","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.10149","title":"Semantic Labeling for Third-Party Cybersecurity Risk Assessment: A Semi-Supervised Approach to Intent-Aware Question Retrieval","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2604.04456","title":"Empirical Characterization of Rationale Stability Under Controlled Perturbations for Explainable Pattern Recognition","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2604.16351","title":"Training for Compositional Sensitivity Reduces Dense Retrieval Generalization","created":"2026-03-16","cited_by_count":0,"area":null},{"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":"2605.07158","title":"Topic Is Not Agenda: A Citation-Community Audit of Text Embeddings","created":"2026-05-08","cited_by_count":0,"area":"rag"},{"id":"2605.11022","title":"SCOPE: Siamese Contrastive Operon Pair Embeddings for Functional Sequence Representation and Classification","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.22099","title":"A Comparative Study of Language Models for Khmer Retrieval-Augmented Question Answering","created":"2026-05-21","cited_by_count":0,"area":"rag"},{"id":"2606.29571","title":"Anisotropy Decides Cosine vs. Rank Metrics for Text Embeddings","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.03581","title":"PLGSA-Transformer: Periocular Landmark-Guided Attention with Occlusion-Adaptive Cosine Thresholding for Cross-Modal Masked and Unmasked Face Recognition","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.13660","title":"The Hyperspherical Geometry of CLIP Latent Space: A Semantic Mixture Model","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.26060","title":"Large-Scale ChatBot Validation Through Customer Digital Twin Simulations","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2608.04170","title":"Visualizing Graph-to-Answer Mechanism Recovery in Materials-Science Hypothesis Generation","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.05393","title":"Adapting Vision Foundation Models with Cascaded Semantics","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.15325","title":"Logical Embeddings for Argument Analysis","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2608.24825","title":"A Dual-Dimensional LLM Framework for Automated Item Incidental Content Similarity Analysis in Large-Scale Assessments","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.06663","title":"ECOKV: Geometry-Aware KV Cache Eviction via Complementary Diversity Metrics","created":"2026-09-06","cited_by_count":0,"area":"mllm"},{"id":"2609.15640","title":"Human-Grounded Calibration for Long-Text Image-Text Congruence in Vision-Language Models","created":"2026-09-14","cited_by_count":0,"area":"mllm"},{"id":"2609.19006","title":"WordPolo: Evaluating Language Models Through Iterative Semantic Feedback","created":"2026-07-18","cited_by_count":0,"area":"lr"},{"id":"2609.33936","title":"How Strong Is the Evidence for the Artificial Hivemind? Reevaluating Evidence for the Open-Ended Homogeneity of Language Models","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.38929","title":"Learning What to Forget: Distributional Unlearning for LLM Representation Spaces","created":"2026-09-30","cited_by_count":0,"area":"safety"}],"next_cursor":null}