{"total":97,"rows":[{"id":"2509.20354","title":"EmbeddingGemma: Powerful and Lightweight Text Representations","created":"2025-09-24","cited_by_count":139,"area":null},{"id":"2412.08821","title":"Large Concept Models: Language Modeling in a Sentence Representation Space","created":"2024-12-11","cited_by_count":89,"area":null},{"id":"2506.18902","title":"jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval","created":"2025-06-23","cited_by_count":76,"area":null},{"id":"2412.04506","title":"Arctic-Embed 2.0: Multilingual Retrieval Without Compromise","created":"2024-12-03","cited_by_count":58,"area":null},{"id":"2504.14693","title":"Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark","created":"2025-04-20","cited_by_count":37,"area":null},{"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":"2412.12591","title":"LLMs are Also Effective Embedding Models: An In-depth Overview","created":"2024-12-17","cited_by_count":32,"area":null},{"id":"2503.01776","title":"Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation","created":"2025-03-03","cited_by_count":26,"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":"2505.18366","title":"Hard Negative Mining for Domain-Specific Retrieval in Enterprise Systems","created":"2025-05-23","cited_by_count":14,"area":null},{"id":"2508.21290","title":"Efficient Code Embeddings from Code Generation Models","created":"2025-08-29","cited_by_count":13,"area":null},{"id":"2412.13102","title":"AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark","created":"2024-12-17","cited_by_count":12,"area":null},{"id":"2410.18634","title":"Little Giants: Synthesizing High-Quality Embedding Data at Scale","created":"2024-10-24","cited_by_count":11,"area":null},{"id":"2411.01192","title":"Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks","created":"2024-11-02","cited_by_count":10,"area":null},{"id":"2502.11571","title":"FaMTEB: Massive Text Embedding Benchmark in Persian Language","created":"2025-02-17","cited_by_count":10,"area":null},{"id":"2504.07199","title":"SemEval-2025 Task 5: LLMs4Subjects -- LLM-based Automated Subject Tagging for a National Technical Library's Open-Access Catalog","created":"2025-04-09","cited_by_count":10,"area":null},{"id":"2509.24789","title":"Fidel-TS: A High-Fidelity Multimodal Benchmark for Time Series Forecasting","created":"2025-09-29","cited_by_count":10,"area":null},{"id":"2505.20422","title":"SEMMA: A Semantic Aware Knowledge Graph Foundation Model","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2507.15339","title":"LionGuard 2: Building Lightweight, Data-Efficient & Localised Multilingual Content Moderators","created":"2025-07-21","cited_by_count":7,"area":null},{"id":"2411.08127","title":"TIPO: Text to Image with Text Presampling for Prompt Optimization","created":"2024-11-12","cited_by_count":6,"area":null},{"id":"2412.08329","title":"BEIR-NL: Zero-shot Information Retrieval Benchmark for the Dutch Language","created":"2024-12-11","cited_by_count":6,"area":null},{"id":"2505.17134","title":"LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2602.05735","title":"CSRv2: Unlocking Ultra-Sparse Embeddings","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2603.17605","title":"ReLaGS: Relational Language Gaussian Splatting","created":"2026-03-18","cited_by_count":6,"area":null},{"id":"2412.07462","title":"Bilingual BSARD: Extending Statutory Article Retrieval to Dutch","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2509.12340","title":"MTEB-NL and E5-NL: Embedding Benchmark and Models for Dutch","created":"2025-09-15","cited_by_count":5,"area":null},{"id":"2510.02330","title":"EntropyLong: Effective Long-Context Training via Predictive Uncertainty","created":"2025-09-26","cited_by_count":5,"area":null},{"id":"2507.13105","title":"SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstracts","created":"2025-07-17","cited_by_count":4,"area":null},{"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":"2508.13773","title":"PENGUIN: Enhancing Transformer with Periodic-Nested Group Attention for Long-term Time Series Forecasting","created":"2025-08-19","cited_by_count":3,"area":null},{"id":"2508.20736","title":"Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guarantees","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2509.00842","title":"Negative Matters: Multi-Granularity Hard-Negative Synthesis and Anchor-Token-Aware Pooling for Enhanced Text Embeddings","created":"2025-08-31","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":"2512.14277","title":"SPARQL-LLM: Real-Time SPARQL Query Generation from Natural Language Questions","created":"2025-12-16","cited_by_count":3,"area":null},{"id":"2604.05821","title":"CLEAR: Cross-Lingual Enhancement in Alignment via Reverse-training","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2505.08435","title":"Hakim: Farsi Text Embedding Model","created":"2025-05-13","cited_by_count":2,"area":null},{"id":"2505.14984","title":"CRAFT: Training-Free Cascaded Retrieval for Tabular QA","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2508.11442","title":"CoDiEmb: A Collaborative yet Distinct Framework for Unified Representation Learning in Information Retrieval and Semantic Textual Similarity","created":"2025-08-15","cited_by_count":2,"area":null},{"id":"2508.12243","title":"SEA-BED: How Do Embedding Models Represent Southeast Asian Languages?","created":"2025-08-17","cited_by_count":2,"area":null},{"id":"2509.24906","title":"Neural network embeddings recover value dimensions from psychometric survey items on par with human data","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2510.00662","title":"Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generation","created":"2025-10-01","cited_by_count":2,"area":null},{"id":"2510.15577","title":"BiMax: Bidirectional MaxSim Score for Document-Level Alignment","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2510.15691","title":"Exploring the Synergy of Quantitative Factors and Newsflow Representations from Large Language Models for Stock Return Prediction","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2512.16439","title":"From Essence to Defense: Adaptive Semantic-aware Watermarking for Embedding-as-a-Service Copyright Protection","created":"2025-12-18","cited_by_count":2,"area":null},{"id":"2601.03798","title":"Where meaning lives: Layer-wise accessibility of psycholinguistic features in encoder and decoder language models","created":"2026-01-07","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":"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":"2501.00874","title":"LUSIFER: Language Universal Space Integration for Enhanced Multilingual Embeddings with Large Language Models","created":"2025-01-01","cited_by_count":1,"area":null},{"id":"2505.22118","title":"Multilingual vs Crosslingual Retrieval of Fact-Checked Claims: A Tale of Two Approaches","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2507.02205","title":"Team RAS in 9th ABAW Competition: Multimodal Compound Expression Recognition Approach","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2510.22369","title":"GigaEmbeddings: Efficient Russian Language Embedding Model","created":"2025-10-25","cited_by_count":1,"area":null},{"id":"2512.21598","title":"From Shallow Humor to Metaphor: Towards Label-Free Harmful Meme Detection via LMM Agent Self-Improvement","created":"2025-12-25","cited_by_count":1,"area":null},{"id":"2602.07309","title":"Semantic Search At LinkedIn","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2605.00297","title":"Trident: Improving Malware Detection with LLMs and Behavioral Features","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.04615","title":"Beyond Retrieval: A Multitask Benchmark and Model for Code Search","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.12714","title":"Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.24079","title":"TRACER: A Semantic-Aware Framework for Fine-Grained Contamination Detection in Code LLMs","created":"2026-05-22","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":"2605.30120","title":"No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.30682","title":"ALM2Vec: Learning Audio Embeddings for Universal Audio Retrieval with Large Audio-Language Models","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2608.15224","title":"Structuring Semantic Embeddings for Principle Evaluation: A Prototype-Guided Contrastive Learning Approach","created":"2026-08-15","cited_by_count":1,"area":null},{"id":"2504.14707","title":"FLAME: A New Dataset on FLemish Accounts of Momentary Experiences","created":"2025-04-20","cited_by_count":0,"area":null},{"id":"2505.16460","title":"University of Indonesia at SemEval-2025 Task 11: Evaluating State-of-the-Art Encoders for Multi-Label Emotion Detection","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2505.20190","title":"A Text-Based Recommender System that Leverages Explicit Affective State Preferences","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2506.01254","title":"Memory-Efficient FastText: A Comprehensive Approach Using Double-Array Trie Structures and Mark-Compact Memory Management","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2506.05991","title":"A Culturally-Rich Romanian NLP Dataset from \"Who Wants to Be a Millionaire?\" Videos","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2506.12092","title":"Enhancing Traffic Accident Classifications: Application of NLP Methods for City Safety","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2506.21913","title":"HyReC: Exploring Hybrid-based Retriever for Chinese","created":"2025-06-27","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":"2510.04626","title":"Compressed Concatenation of Small Embedding Models","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2510.07566","title":"Multi-Task Pre-Finetuning of Lightweight Transformer Encoders for Text Classification and NER","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2510.15330","title":"BeLLMan: Controlling LLM Congestion","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2510.24690","title":"Bridging Tool Dependencies and Domain Knowledge: A Graph-Based Framework for In-Context Planning","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2601.03450","title":"Soft Contextualized Encoder For User Defined Text Classification","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.10096","title":"Multilingual-To-Multimodal (M2M): Unlocking New Languages with Monolingual Text","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2601.22439","title":"Stop Jostling: Adaptive Negative Sampling Reduces the Marginalization of Low-Resource Language Tokens by Cross-Entropy Loss","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.04812","title":"Robust Generalizable Heterogeneous Legal Link Prediction","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.08282","title":"Using Multimodal and Language-Agnostic Sentence Embeddings for Abstractive Summarization","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.19283","title":"Automated Motif Indexing on the Arabian Nights","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2604.07809","title":"PolicyLong: Towards On-Policy Context Extension","created":"2026-04-09","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":"2604.20720","title":"COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.13415","title":"KIT-TIP-NLP at MultiPride: Continual Learning with Multilingual Foundation Model","created":"2026-05-13","cited_by_count":0,"area":null},{"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":"2605.23420","title":"Naturalistic measure of social norms alignment","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.13537","title":"When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval","created":"2026-06-11","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":"2606.22807","title":"Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Reranking","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.30625","title":"Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.14882","title":"Does generative AI supersede supervised XMLC? A Benchmark Study on Automated Subject Indexing with German Scientific Literature","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.14967","title":"Latent Trajectory Discrimination for AI-Generated Text Detection","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.22662","title":"CuraWeb: Joint Optimization of Quality, Redundancy, and Diversity for Web-Scale Pretraining Data","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.10636","title":"DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.00831","title":"FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.12674","title":"Doc2FRC: Length-Consistent Document-Level Machine Translation via Fixed-Range Chunking","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.29684","title":"DP-IPI: A Hybrid Differential Privacy Text Rewriting Mechanism for Indirect Personal Identifiers in Clinical Texts","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2610.02875","title":"Query-aware routing for Cross-lingual performance gains in Encoders","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}