Text Embeddings

Follow this topic Ask about this topic

Momentum

24 papers in the last four weeks, up 100% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 203

All topics

Learning to Retrieve via Reinforcement Learning in Embedding Space
Oct 6, 2026Qi Liu, Fengming Liang, Yiqun Chen +2Retrieval Layer Text Embeddings
Renmin University of China
A Safe Prototype Is Not a Safety Direction: Reference Dependence and Prompt Confounds in Response-Safety Embeddings
Oct 1, 2026Sahil KadadekarPrompt-Injection Detectors Text Embeddings
New York University
STAGE: Subspace-Targeted Affine Generative Erasure for Text-to-3D Models
Oct 1, 2026Karol Dziekan, Przemysław Spurek, Dawid Malarz3D Generative Models High-Fidelity 3D Generation
Jagiellonian University · IDEAS Research Institute
Scaling and Distilling Text Embeddings for Better Diffusibility
Oct 1, 2026Zekai Zhang, Yunjie Tian, Yanjin He +4Diffusion Language Models Text Embeddings
University of Michigan
Efficient Task Adaptation in Large Language Models: A Survey of Weight-Based, Prompt-Based, and Embedding-Based Adaptations
Oct 1, 2026Jungwon Park, Changin Choi, Jimyeong Kim +2Efficient Task Adaptation Parameter-Efficient Adaptation
RICS · Daegu Gyeongbuk Institute of Science and Technology · IPAI +3
Effective Dense Retrieval using Only In-Context Examples
Sep 29, 2026Nour Jedidi, Abdul Basit Ali, Hang Li +1Retrieval Layer Text Embeddings
University of Waterloo · The University of Queensland
SALI: Shot-Aware Late Interaction for Cross-Shot Relation Matching in Text-to-Video Retrieval using Film-Grammar Knowledge
Sep 24, 2026Toya Oyama, Rainer Lienhart, Shin'ichi SatohRelation Extraction Multimodal Retrieval
The University of Tokyo · National Institute of Informatics · University of Augsburg
TEMPS: Temporal Sentence Embeddings for Temporal Information Retrieval
Sep 23, 2026Mourad Hassani, Julien Romero, Amel Bouzeghoub +1Timestep Embeddings Text Embeddings
SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris, France · Aldebaran Care, France
BELXTR: Biomedical Entity Linking via Contextualized Token Retrieval
Sep 22, 2026Samuele Garda, Ulf LeserMedical Ontology Information Extraction
Computer Science, Humboldt-Universität zu Berlin, Rudower Chaussee 25, 12489, Berlin, Germany
MIND the Gap: A Geographic Implicit Neural Representation with Adjustable Spatial Scale
Sep 21, 2026Isaac Corley, Arjun Rao, Esther Rolf +7Neural Representations Text Embeddings
Taylor Geospatial · University of British Columbia · Vector Institute +7
Learnable Classifier-Free Guidance Null Embeddings for Enhanced Controllable Speech Synthesis
Sep 21, 2026Biel Tura Vecino, Yoach Lacombe, Julian Weber +4Speech Synthesis Classifier-Free Guidance
Cantina Labs
InterHier: Learning Interconnected Hierarchical Semantics for Open-Vocabulary Object Detection
Sep 21, 2026Yeong-Jin Kim, Ho-Joong Kim, Seong-Whan LeeOpen-Vocabulary Object Detection Semantic Representations
Department of Artificial Intelligence, Korea University, Seoul 02841, Republic of Korea
Embedding Models Measure in Peculiar Ways
Sep 17, 2026Juri Opitz, Andrianos MichailText Embeddings Semantic Geometry
Dept. of Computational Linguistics University of Zurich
MetaRTL: Meta-path Attention Enhanced Relational Table Learning
Sep 17, 2026Ken Zhong, Weichen Li, Zheng WangRelational Deep Learning Relational
School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · Shanghai Key Laboratory of Integrated Administration Technologies for Information Security, Shanghai, China
Beyond Embedding Transfer: Component Roles in Grokking Transfer and Stability
Sep 16, 2026Zeyu JiaText Embeddings Dissociation
Tianjin Medical University
Repurposing Unified Topological Signatures for Graph Representation Learning
Sep 15, 2026Sanyam Sanjay Jain, Anshika Krishnatray, Aditya Sharma +1Graph Representation Learning Graph Neural Networks
BITS Pilani, India
Multi-modal Knowledge Preserving Adapter for Embedding Backward Compatibility
Sep 15, 2026Jaeseok Byun, Gukyeong Kwon, Han-Kai Hsu +4Multimodal Embeddings Large Language Model Adaptation
1Seoul National University, South Korea · 2Amazon AGI, USA
Reduplicative constructions in Mandarin: Socio-emotional profiling through distributional semantics
Sep 15, 2026Chaoyi Wu, Yu-Hsiang Tseng, R. Harald BaayenMandarin Contextual Embeddings
1Beihang University · University of Tübingen
Flexible and Interpretable Accent Distance Measurements
Sep 12, 2026Charles McGhee, Mark J. F. Gales, Kate M. KnillArticulatory Accents
ALTA Institute/MIL, Department of Engineering, University of Cambridge, UK
A Training-Free, Alignment-Free Approach to Corporate Intelligence: Application to SEC Filings
Sep 11, 2026Jean-François DelpechText Corpora Cyber Threat Intelligence
WebGlyphs, Inc. Mesa, AZ 85203
Structural Process Supervision for Latent Chain-of-Thought Reasoning
Sep 9, 2026Yiqi Li, Xu Chen, Chen Ju +5Efficient Latent Reasoning Token-Level Supervision
Shanghai Jiao Tong University · Taobao & Tmall Group
Exact Degeneracy Under Balanced k-Shot Sampling:Consequences for Small-Sample Discriminant Analysis on LLM Embeddings
Sep 9, 2026Lingxiao QuDiscriminative Models Principal Component Analysis
The University of Aizu, Aizuwakamatsu, Fukushima, Japan
HypLTSF: A Hyperbolic Geometric View of Multi-Scale Hierarchies for Long-Term Time Series Forecasting
Sep 8, 2026Namwoo Kim, Hyungryul Baik, Yoonjin YoonMultiscale Hyperbolic Space
Urban AI Institute, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea · Department of Mathematical Science, KAIST, Daejeon, Republic of Korea · Department of Civil and Environmental Engineering, KAIST, Daejeon, Republic of Korea
Same Problem, Different Field: Cross-Domain Solution Import via Domain-Stripped Computational Fingerprints
Sep 7, 2026Eryk KulikowskiSimilarity and Metrics Fingerprint
LIBIS KU Leuven Leuven, Belgium
Shadow Queries for Private Retrieval in Vector Databases
Sep 7, 2026Xinguo Feng, Zhongkui Ma, Zihan Wang +4Vector Database Text Embeddings
The University of Queensland, Brisbane, Australia · City University of Hong Kong, Hong Kong · CSIRO’s Data 61, Sydney, Australia
CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation
Sep 3, 2026Tingyu Song, Mingxin Li, Yanzhao Zhang +5Cross-Encoder Reranking Text Embeddings
CASIA · Alibaba Group · University of Chinese Academy of Sciences +1
Synthetic Semantic Supervision for Contrastive Code Representation Learning in Small Transformers: An Empirical Study
Sep 3, 2026Kenneth Paulsen, Florian Tambon, Mike Papadakis +1Text Embeddings Contrastive Learning
University of Luxembourg (SnT) · School of Computing, KAIST
Tree species mapping in Denmark: A comparison of spectral-temporal features with geospatial foundation model embeddings
Sep 3, 2026Alkiviadis Koukos, Spyros Kondylatos, Thomas Nord-Larsen +3Forest Biomass Geospatial Foundation Models
EO Centre of Excellence, DHI, Agern Alle 5, Hørsholm, 2970, Denmark · Department of Geoscience and Natural Resource Management, University of Copenhagen, Øster Voldgade 10, Copenhagen, 1350, Denmark · ceometrics, Strandvejen 273C, Charlottenlund, 2920, Denmark
SAM3-LoRA: Parameter-Efficient Adaptation of a Concept-Promptable Foundation Model for Multi-Class Structural Defect Segmentation
Aug 31, 2026P. Malaisree, S. Youwai, S. Janrungautai +3Few-Shot Segmentation Wireless Foundation Models
MAA Consultants Co., Ltd. · AI Research Group, Department of Civil Engineering, Faculty of Engineering, King Mongkut´s University of Technology Thonburi (KMUTT). · School of Engineering, University of Phayao. +2
Location-Aware Language Models via Secondary Embeddings
Aug 31, 2026Gokul Srinivasagan, Munir GeorgesSemantic Geometry Text Embeddings
AImotion Bavaria, Technische Hochschule Ingolstadt, Germany
Hidden relationships in a document-derived property graph: top-k chunk embeddings and inverse-distance weighting over a dynamically evolving ontology
Aug 31, 2026Bilge Kaan Karamete, Hunter CastenKnowledge Graph Embeddings Knowledge Graphs
Babel Street
Do General NLP Embeddings Capture Ontological Reasoning?
Aug 31, 2026Hamed Babaei Giglou, Jennifer D'Souza, Sören AuerOntology Text Embeddings
TIB Leibniz Information Centre for Science and Technology · Hannover, Lower Saxony, Germany · L3S Research Center, Leibniz University of Hannover
When Can We Work in Embedding Space? What Text Embeddings Preserve
Aug 31, 2026Simon FreyaldenhovenText Embeddings Text Analysis and Detection
Federal Reserve Bank of Philadelphia
Generative Retrieval for E-commerce: Jointly Learning Embedding and Codebook with Same Product Cluster
Aug 31, 2026Songtao Fang, Zihao Xu, Shaowei Wei +2Text Embeddings Codebooks
Alibaba Group HangZhou, CHINA
Who Remains, What Changes: Identity Anchored Composed Gait Retrieval
Aug 27, 2026Jingchen Fei, Zengbin Wang, Yukun Liu +3Gait Analysis Re-Identification
Beijing University of Posts and Telecommunications · Huazhong University of Science and Technology
The Embedder's Dilemma: LLMs Are Better, but at What Cost?
Aug 13, 2026Adnan El Assadi, Niklas Muennighoff, Jinhyuk LeeText Embeddings LLM Inference Optimization
Harvard University · Stanford University · Independent Researcher
Dynamic Distribution-Aware Uncertainty Tracking in Vision-Language Representation Learning
Aug 10, 2026Ao Zhou, Zhiwei Jiang, Zifeng Cheng +4Recent Vision-Language Models Uncertainty
State Key Laboratory of Novel Software Technology, Nanjing University
SCALE: Scientific Concept Aggregation via LLMs and Embeddings for Fine-Grained Taxonomy Extension
Aug 7, 2026Daniele Raimondi, Feichi Lu, Oliver Grun +2Taxonomy Scientific Discovery
MDPI Data Intelligence Team, MDPI AG, Grosspeteranlage 5, CH-4052 Basel, Switzerland
How Far Do Simple Transformations Translate Across Text Embedding Models?
Aug 6, 2026Sid Ali Hamideche, Louis-Adrien Dufrène, Quentin Lampin +1Text Embeddings Transform Concepts
Orange Research · Orange
InsightEmb: Learning Action-Intent Embeddings for Agentic Insight Retrieval
Aug 5, 2026Tsz Ting Chung, Jiangnan Li, Jie Zhou +1Agentic Reasoning Insights
1The Hong Kong University of Science and Technology · 2WeChat AI, Tencent
Neighborhood-Aware Dual Biomedical Entity Linking
Aug 4, 2026Yicheng Tao, Jie LiuMedical Ontology Entities
Department of Electrical Engineering and Computer Science, University of Michigan · Gilbert S. Omenn Department of Computational Medicine and Bioinformatics, University of Michigan
Perceptual Anchoring: Prototype-Guided Text Calibration for Training-free Open-Vocabulary Semantic Segmentation
Aug 4, 2026Wanli Ma, Jiangwen Lu, Qinmu Peng +1Open-Vocabulary Segmentation Text Embeddings
School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China · National Anti-counterfeit Engineering Research Center, Huazhong University of Science and Technology, Wuhan 430074, China · School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China
Enhancing Tabular Learners with Context-Aware Semantic Embeddings
Aug 4, 2026Günther Schindler, Maximilian Schambach, Johannes HöhneTabular Learning Text Embeddings
SAP SE
Self-supervised DXA representations encode multi-system disease risk, biological aging and heritability
Aug 3, 2026Gil Sasson, Zachary Levine, Smadar Shilo +9Vascular Age Biomarker
Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot, Israel. · Gray Faculty of Medical and Health Sciences, Tel Aviv University, Tel-Aviv, Israel. · The Jesse Z and Sara Lea Shafer Institute for Endocrinology and Diabetes, National Center for Childhood Diabetes, Schneider Children’s Medical Center of Israel, Petah Tikva, Israel. +5
AdaForensics: Learning A Characteristic-aware Adaptive Deepfake Detector
Aug 3, 2026Xiaoke Yang, Haixu Song, Xiangyu Lu +2Deepfake Detection Digital Forensics
Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Department of Electronic Engineering, Tsinghua University, Beijing, China
UniqueSplat: View-conditioned 3D Gaussian Splatting for Generalizable 3D Reconstruction
Aug 3, 2026Haixu Song, Xiaoke Yang, Shengjun Zhang +2Feed-Forward 3D Gaussian Splatting Recent 3D Gaussian Splatting
Tsinghua University, China
Pretraining on Call Graphs: When Binary Analysis Tasks Profit From Context
Aug 3, 2026Samuel Valenzuela, Johannes KinderReverse Engineering Text Embeddings
Ludwig-Maximilians-Universität München · Munich Center for Machine Learning · Center for Digital Technology and Management +1
Foveated Probes Recover Localized Binding Information in Vision Foundation Models
Aug 1, 2026Mateusz Michalkiewicz, Mahsa Baktashmotlagh, Guha BalakrishnanFrozen Vision-Language Models Vision Foundation Models
Rice University, Houston, TX, USA · The University of Queensland, Brisbane, QLD, Australia
Bridging the Question-Answer Gap in Retrieval-Augmented Generation: Hypothetical Prompt Embeddings
Jul 31, 2026Domen Vake, Jernej Vičič, Aleksandar TošićText Embeddings Prompt Engineering
University of Primorska, Faculty of Mathematics, Natural Sciences and Information Technologies · InnoRenew CoE · Research Centre of the Slovenian Academy of Sciences and Arts, The Fran Ramovš Institute
Tokenizer-Agnostic Engram Module
Jul 31, 2026Jia Peng Lim, Hai Leong ChieuDeepseek Text Embeddings
Singapore Management University · DSO National Laboratories
CADENCE: A Cardiac Atom Dictionary for Interpretable Neural Concept Extraction from ECG Foundation Models
Jul 28, 2026Yixuan Duan, Arjun Naik, Sadeer Al-Kindi +1Electrocardiogram Foundation Models Cardiac
Department of Electrical and Computer Engineering Rice University Houston, Texas, USA · Department of Computer Science Rice University Houston, Texas, USA · Department of Cardiology Houston Methodist Hospital Houston, Texas, USA
Memory Layer: Train the In-Model Cache for Recommendation Models
Jul 27, 2026Liangyuan Na, Gufan Yin, Yixin Bao +19Text Embeddings Cache
Meta
Human Preference aligned Tabular Similarity
Jul 27, 2026Frederik Hoppe, Astrid Franz, Marianne Michaelis +2Similarity and Metrics Text Embeddings
CONTACT Software GmbH, Bremen, Germany
TEmBed-T: A Multi-Dimensional Benchmark for Table-Level Embeddings
Jul 27, 2026Ayeen Poostforoushan, Liane Vogel, Carsten BinnigText Embeddings Multi-Turn Benchmark
Independent Researcher · Technical University of Darmstadt · Technical University of Darmstadt & DFKI & hessian.AI
Choosing a Text Embedding Model: A Practical Benchmarking and Decision Framework
Jul 26, 2026Madhav S BaidyaText Embeddings Text Analysis and Detection
Indian Institute of Technology (BHU) Varanasi
A Comparative Evaluation of Embeddings and LLMs in a Greek Book Publisher Setting - The CUP Dataset
Jul 23, 2026Katerina Papantoniou, Panagiotis Papadakos, Theodore Patkos +3Greek Text Embeddings
ICS-FORTH Heraklion, Greece · Crete University Press Heraklion, Greece · University of Crete, Computer Science Department, Heraklion, Greece
Evaluating and Mitigating Gender Bias in Pre-trained Embeddings for ML-based Recruitment
Jul 22, 2026Farnaz Faramarzi Lighvan, Lynn HouthuysGender Bias Gender
AI Lab, Vrije Universiteit Brussel, Belgium
Fusion Embedding: A Unified Embedding Space for Text, Image, Video, and Audio
Jul 21, 2026Abdul Basit Tonmoy, Kazi Fardinul Hoque, Md. Shahrier Islam Arham +1Text-To-Audio Multimodal Embeddings
1Eximius Labs · 2Wabash College · 3Skop Intelligence Co.
DARA: Degradation-Aware Low-Rank Residual Adaptation with Original-to-Corrupted Distillation for Corruption-Robust Animal Re-Identification
Jul 18, 2026Cynthia Xie, Talia XuAnimal Re-Identification Re-Identification
The University of Auckland Auckland, New Zealand
KeySI: An Interaction Framework for Tuning Text Embeddings Based on Human Feedback
Jul 17, 2026Yan Zhu, Y. Chen, Rebecca FaustText Embeddings Hierarchical Semantic Alignment
Yan Zhu is with Tulane University. · Y. Chen is with Tulane University. · Rebecca Faust* is with Tulane University.

Oct 6, 2026, cs.IRJ/K move · Enter open · S save

Learning to Retrieve via Reinforcement Learning in Embedding Space

Qi Liu, Fengming Liang, Yiqun Chen, Erhan Zhang+1

Renmin University of China

Retrieval Layer Text Embeddings

Open paper AskPDF arXiv

Dense retrieval models are typically trained with contrastive objectives that learn effective representations but do not directly optimize retrieval metrics or downstream task performance. To address this problem, we introduce RELER (REinforcement LEarning for Retrieval), a reinforcement learning framework that enables existing embedding models to learn to retrieve directly in embedding space and align to task-specific rewards. We train RELER by sampling unit-length query and document embedding actions from von Mises-Fisher (vMF) distributions centered on normalized encoder outputs, scoring the resulting retrieval or downstream outcomes as rewards, and updating the encoder with REINFORCE using a leave-one-out baseline (RLOO). As exploration in the high-dimensional embedding space is prone to sampling noise, we further propose conditional-mean projection (CMP), which projects each sampled embedding onto the low-dimensional subspace spanned by its encoder output and the candidate embeddings it is compared against, reducing noise in the policy gradient while preserving its expectation. We evaluate RELER on BRIGHT, a benchmark with reasoning-intensive queries that remain challenging for existing embedding models. RELER consistently outperforms InfoNCE and LambdaLoss in average nDCG@10 when post-training BGE-M3 and Qwen3-Embedding backbones. We further evaluate downstream utility through retrieval-augmented generation (RAG), where we adapt only the query encoder while keeping the document index and generator fixed. Across seven QA datasets, jointly optimizing retrieval and answer rewards improves both average retrieval performance and answer quality in RAG.

Momentum

Related topics

Latest papers 203