{"total":139,"rows":[{"id":"2512.10942","title":"VL-JEPA: Joint Embedding Predictive Architecture for Vision-language","created":"2025-12-11","cited_by_count":68,"area":"mllm"},{"id":"2510.27350","title":"RzenEmbed: Towards Comprehensive Multimodal Retrieval","created":"2025-10-31","cited_by_count":29,"area":"mllm"},{"id":"2512.14856","title":"T5Gemma 2: Seeing, Reading, and Understanding Longer","created":"2025-12-16","cited_by_count":17,"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":"2601.10592","title":"Action100M: A Large-scale Video Action Dataset","created":"2026-01-15","cited_by_count":12,"area":null},{"id":"2601.10825","title":"Reasoning Models Generate Societies of Thought","created":"2026-01-15","cited_by_count":12,"area":"lr"},{"id":"2603.19223","title":"F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World","created":"2026-03-19","cited_by_count":12,"area":null},{"id":"2601.04575","title":"Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playing","created":"2026-01-08","cited_by_count":11,"area":"lr"},{"id":"2511.18491","title":"MindEval: Benchmarking Language Models on Multi-turn Mental Health Support","created":"2025-11-23","cited_by_count":10,"area":null},{"id":"2601.12910","title":"SciCoQA: Quality Assurance for Scientific Paper--Code Alignment","created":"2026-01-19","cited_by_count":10,"area":"agents"},{"id":"2602.11151","title":"Diffusion-Pretrained Dense and Contextual Embeddings","created":"2026-02-11","cited_by_count":9,"area":null},{"id":"2602.05216","title":"Semantic Search over 9 Million Mathematical Theorems","created":"2026-02-05","cited_by_count":8,"area":null},{"id":"2602.15313","title":"Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory","created":"2026-02-17","cited_by_count":8,"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":"2607.27178","title":"DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search","created":"2026-07-29","cited_by_count":6,"area":null},{"id":"2510.04373","title":"JEF-Hinter: Leveraging Offline Knowledge for Improving Web Agents Adaptation","created":"2025-10-05","cited_by_count":5,"area":"agents"},{"id":"2510.07048","title":"Search-R3: Unifying Reasoning and Embedding in Large Language Models","created":"2025-10-08","cited_by_count":4,"area":"lr"},{"id":"2603.23607","title":"Reasoning models do not yet follow their reasoning in autonomous driving: The KITScenes LongTail Dataset","created":"2026-03-24","cited_by_count":4,"area":"lr"},{"id":"2510.06730","title":"PTEB: Towards Robust Text Embedding Evaluation via Stochastic Paraphrasing at Evaluation Time with LLMs","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2510.23896","title":"AfriMTEB and AfriE5: Benchmarking and Adapting Text Embedding Models for African Languages","created":"2025-10-27","cited_by_count":3,"area":"rag"},{"id":"2512.21332","title":"C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling","created":"2025-12-24","cited_by_count":3,"area":null},{"id":"2602.22752","title":"Towards Simulating Social Media Users with LLMs: Evaluating the Operational Validity of Conditioned Comment Prediction","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2603.02098","title":"Efficient and High-Fidelity Omni Modality Retrieval","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2603.03379","title":"MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning","created":"2026-03-03","cited_by_count":3,"area":"lr"},{"id":"2604.11322","title":"Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations","created":"2026-04-13","cited_by_count":3,"area":null},{"id":"2605.23556","title":"Is Dimensionality a Barrier for Retrieval Models?","created":"2026-05-22","cited_by_count":3,"area":null},{"id":"2607.01977","title":"OntoLearner: A Modular Python Library for Ontology Learning with Large Language Models","created":"2026-07-02","cited_by_count":3,"area":null},{"id":"2601.16018","title":"Mecellem Models: Turkish Models Trained from Scratch and Continually Pre-trained for the Legal Domain","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2603.10876","title":"An Extreme Multi-label Text Classification (XMTC) Library Dataset: What if we took \"Use of Practical AI in Digital Libraries\" seriously?","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2604.03420","title":"Zero-Shot Quantization via Weight-Space Arithmetic","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2605.04018","title":"Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems","created":"2026-05-05","cited_by_count":2,"area":"agents"},{"id":"2605.30497","title":"CanLegalRAGBench: Evaluating Retrieval-Augmented Generation on Canadian Case Law","created":"2026-05-28","cited_by_count":2,"area":"rag"},{"id":"2605.31142","title":"On the Robustness of Multilingual Text Embedding Rankings Across Learning Tasks, Languages, and Benchmark Datasets","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2606.16408","title":"MUNI: Multimodal Unified Latent Diffusion for Coherent Any-to-Any Generation","created":"2026-06-15","cited_by_count":2,"area":"diffusion"},{"id":"2606.20627","title":"Latent Goal Prediction from Language for Model-Based Planning","created":"2026-05-26","cited_by_count":2,"area":"wm"},{"id":"2511.07969","title":"Unified Work Embeddings: Contrastive Learning of a Bidirectional Multi-task Ranker","created":"2025-11-11","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":"2602.07739","title":"HypRAG: Hyperbolic Dense Retrieval for Retrieval Augmented Generation","created":"2026-02-08","cited_by_count":1,"area":"rag"},{"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":"2602.23949","title":"HotelQuEST: Balancing Quality and Efficiency in Agentic Search","created":"2026-02-27","cited_by_count":1,"area":"agents"},{"id":"2603.06999","title":"TrajPred: Trajectory-Conditioned Joint Embedding Prediction for Surgical Instrument-Tissue Interaction Recognition in Vision-Language Models","created":"2026-03-07","cited_by_count":1,"area":"mllm"},{"id":"2604.03529","title":"Incentives shape how humans co-create with generative AI","created":"2026-04-04","cited_by_count":1,"area":null},{"id":"2604.08851","title":"Cross-Lingual Attention Distillation with Personality-Informed Generative Augmentation for Multilingual Personality Recognition","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2604.14547","title":"Predicting Post-Traumatic Epilepsy from Clinical Records using Large Language Model Embeddings","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2605.06276","title":"Linear Semantic Segmentation for Low-Resource Spoken Dialects","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.12522","title":"Differences in Text Generated by Diffusion and Autoregressive Language Models","created":"2026-04-04","cited_by_count":1,"area":"diffusion"},{"id":"2605.17000","title":"BoLT: A Benchmark to Democratize Black-box Optimization Research for Expensive LLM Tasks","created":"2026-05-16","cited_by_count":1,"area":null},{"id":"2606.11257","title":"Energy-Efficient On-Device RAG on a Mobile NPU: System Design and Benchmark on Snapdragon X Elite","created":"2026-06-09","cited_by_count":1,"area":"rag"},{"id":"2606.12666","title":"CAPED: Context-Aware Privacy Exposure Defense for Mobile GUI Agents","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.13100","title":"LEDGER: A Long-Context Benchmark of Corporate Annual Reports for Grounded Financial Retrieval and Extraction","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.18801","title":"SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2606.19057","title":"Quantifying and Auditing LLM Evaluation via Positive--Unlabeled Learning","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2606.29894","title":"SABER-Math: Automated Benchmark for Information Retrieval Evaluation in Mathematics","created":"2026-06-29","cited_by_count":1,"area":"agents"},{"id":"2607.00171","title":"ALEE: Any-Language Evaluation of Embeddings via English-Centric Minimal Pairs","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.04782","title":"Predicting Drafted Deck Strength for \"Magic: the Gathering\"","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2609.00683","title":"Creative Generation via Multi-Agent Debate: Does Debate Suppress Diversity?","created":"2026-09-01","cited_by_count":1,"area":"agents"},{"id":"2509.23340","title":"CrediBench: Building Web-Scale Network Datasets for Information Integrity","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2510.14274","title":"Retrofitting Small Multilingual Models for Retrieval: Matching 7B Performance with 300M Parameters","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2510.24672","title":"Eigenfunction Extraction for Ordered Representation Learning","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2601.03435","title":"The Critical Role of Aspects in Measuring Document Similarity","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.03496","title":"STELLA: Self-Reflective Terminology-Aware Framework for Building an Aerospace Information Retrieval Benchmark","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2601.04824","title":"SOVABench: A Vehicle Surveillance Action Retrieval Benchmark for Multimodal Large Language Models","created":"2026-01-08","cited_by_count":0,"area":"mllm"},{"id":"2601.05851","title":"Router-Suggest: Dynamic Routing for Multimodal Auto-Completion in Visually-Grounded Dialogs","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2601.07861","title":"EmbeddingRWKV: State-Centric Retrieval with Reusable States","created":"2026-01-10","cited_by_count":0,"area":"rag"},{"id":"2601.07995","title":"Is Sentiment Banana-Shaped? Exploring the Geometry and Portability of Sentiment Concept Vectors","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2601.10837","title":"EncodeRec: An Embedding Backbone for Recommendation Systems","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2601.11629","title":"Semantic Differentiation for Tackling Challenges in Watermarking Low-Entropy Constrained Generation Outputs","created":"2026-01-14","cited_by_count":0,"area":"safety"},{"id":"2601.21465","title":"Topeax -- An Improved Clustering Topic Model with Density Peak Detection and Lexical-Semantic Term Importance","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.02524","title":"GASTON: Graph-Aware Social Transformer for Online Networks","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2602.04731","title":"Modular Expert Merging for Biomedical Retrieval","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2602.21379","title":"MrBERT: Modern Multilingual Encoders via Vocabulary, Domain, and Dimensional Adaptation","created":"2026-02-24","cited_by_count":0,"area":null},{"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":"2602.23588","title":"Hyperdimensional Cross-Modal Alignment of Frozen Language and Image Models for Efficient Image Captioning","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.01690","title":"Asking the Right Questions: Ontology-Grounded Interpretable Embeddings for Biomedical Text","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.21047","title":"When Minor Edits Matter: LLM-Driven Prompt Attack for Medical VLM Robustness in Ultrasound","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2604.07095","title":"Multilingual Embedding Probes Fail to Generalize Across Learner Corpora","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.14907","title":"Comparison of Modern Multilingual Text Embedding Techniques for Hate Speech Detection Task","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.17778","title":"TeleEmbedBench: A Multi-Corpus Embedding Benchmark for RAG in Telecommunications","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2604.18199","title":"Linear-Time and Constant-Memory Text Embeddings Based on Recurrent Language Models","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2604.23396","title":"Lost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrieval","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2604.27335","title":"Iterative Definition Refinement for Zero-Shot Classification via LLM-Based Semantic Prototype Optimization","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.00943","title":"ARIS: Agentic and Relationship Intelligence System for Social Robots","created":"2026-05-01","cited_by_count":0,"area":"wm"},{"id":"2605.01831","title":"RMGAP: Benchmarking the Generalization of Reward Models across Diverse Preferences","created":"2026-05-03","cited_by_count":0,"area":"alignment"},{"id":"2605.10339","title":"An Annotation Scheme and Classifier for Personal Facts in Dialogue","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.11374","title":"Test-Time Compute for Frozen Embedding Models through Agentic Program Search","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.16608","title":"To MRL or not to MRL: Text Embeddings are Robust to Truncation Without Matryoshka Learning, Except In Heavy Truncation Scenarios","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.21029","title":"Building a Custom Taxonomy of AI Skills and Tasks from the Ground Up with Job Postings","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.23028","title":"RADAR: Relative Angular Divergence Across Representations","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.24556","title":"The Multilingual Curse at the Retrieval Layer: Evidence from Amharic","created":"2026-05-23","cited_by_count":0,"area":"rag"},{"id":"2605.27168","title":"Grounding Text Embeddings in Stakeholder Associations","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.27767","title":"UniMaia: Steering Chess Policies with Language for Human-like Play","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.29715","title":"User-Aware Active Knowledge Acquisition for Emotional Support Dialogue","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2606.03027","title":"SEA-LION-Embedding: Open and Reproducible Text Embeddings for Southeast Asia","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.12003","title":"Agreement in Representation Space for Open-Ended Self-Consistency","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"id":"2606.13647","title":"SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.18312","title":"TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimization","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.26936","title":"Jailbreaking for the Average Jane: Choosing Optimal Jailbreaks via Bandit Algorithms for Automatically Enhanced Queries","created":"2026-06-25","cited_by_count":0,"area":"safety"},{"id":"2606.28328","title":"TextClusterLab: An Integrated Framework for Reliable Text Clustering Studies","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2606.29580","title":"MAM-AI: An On-Device Medical Retrieval-Augmented Generation System for Nurses and Midwives in Zanzibar","created":"2026-06-28","cited_by_count":0,"area":"rag"},{"id":"2607.04581","title":"MTEB-BR: A Text Embedding Benchmark for Brazilian Portuguese","created":"2026-07-06","cited_by_count":0,"area":null}],"next_cursor":"100"}