Embedding Learning

Shared-AE: Automatic Identification of Shared Subspaces in High-dimensional Neural and Behavioral Activity ICLR 2025 Signed Graph Autoencoder for Explainable and Polarization-Aware Network Embeddings AISTATS 2025 SLR-MVTC: Smooth Low-Rank Multi-View Tensor Clustering AAAI 2025 SMEC:Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression EMNLP 2025 Soft Reasoning Paths for Knowledge Graph Completion IJCAI 2025 SPAC: Sparse Partitioning and Adaptive Core Tensor Pruning Model for Knowledge Graph Completion AAAI 2025 SpaGBOL: Spatial-Graph-Based Orientated Localisation WACV 2025 Speech Vecalign: an Embedding-based Method for Aligning Parallel Speech Documents EMNLP 2025 Static Word Embeddings for Sentence Semantic Representation EMNLP 2025 Statistical Inference of Random Graphs With a Surrogate Likelihood Function JMLR 2025 Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models ACL 2025 Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models ACL 2025 Structural Deep Encoding for Table Question Answering ACL 2025 Structural Entropy Guided Probabilistic Coding AAAI 2025 StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples NAACL 2025 Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks NAACL 2025 TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value Identification ACL 2025 TaxaBind: A Unified Embedding Space for Ecological Applications WACV 2025 TeCoFeS: Text Column Featurization using Semantic Analysis NAACL 2025 Testing Humor Theory Using Word and Sentence Embeddings COLING 2025 The ‘aftermath’ of compounds: Investigating Compounds and their Semantic Representations IJCNLP 2025 The Russian-focused embedders’ exploration: ruMTEB benchmark and Russian embedding model design NAACL 2025 TokAlign: Efficient Vocabulary Adaptation via Token Alignment ACL 2025 TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation CVPR 2025 Tokenization is Sensitive to Language Variation ACL 2025