{"total":122,"rows":[{"id":"2404.00929","title":"A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias","created":"2024-04-01","cited_by_count":84,"area":null},{"id":"2505.12540","title":"Harnessing the Universal Geometry of Embeddings","created":"2025-05-18","cited_by_count":55,"area":null},{"id":"2110.03684","title":"Cross-Domain Imitation Learning via Optimal Transport","created":"2021-10-07","cited_by_count":49,"area":"offlinerl"},{"id":"2211.08775","title":"Unbalanced Optimal Transport, from Theory to Numerics","created":"2022-11-16","cited_by_count":46,"area":null},{"id":"2503.21073","title":"Shared Global and Local Geometry of Language Model Embeddings","created":"2025-03-27","cited_by_count":36,"area":null},{"id":"2103.15375","title":"AlignMixup: Improving Representations By Interpolating Aligned Features","created":"2021-03-29","cited_by_count":33,"area":null},{"id":"2310.09254","title":"GENOT: Entropic (Gromov) Wasserstein Flow Matching with Applications to Single-Cell Genomics","created":"2023-10-13","cited_by_count":28,"area":"diffusion"},{"id":"2305.05080","title":"Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey","created":"2023-05-08","cited_by_count":27,"area":null},{"id":"2208.11726","title":"Wasserstein Task Embedding for Measuring Task Similarities","created":"2022-08-24","cited_by_count":25,"area":null},{"id":"2301.11716","title":"Pre-training for Speech Translation: CTC Meets Optimal Transport","created":"2023-01-27","cited_by_count":25,"area":null},{"id":"2112.03473","title":"Improving Neural Cross-Lingual Summarization via Employing Optimal Transport Distance for Knowledge Distillation","created":"2021-12-07","cited_by_count":22,"area":"distill"},{"id":"2101.00148","title":"Bilingual Lexicon Induction via Unsupervised Bitext Construction and Word Alignment","created":"2021-01-01","cited_by_count":19,"area":null},{"id":"2104.02013","title":"Quantized Gromov-Wasserstein","created":"2021-04-05","cited_by_count":19,"area":null},{"id":"2110.02887","title":"Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings","created":"2021-10-06","cited_by_count":19,"area":null},{"id":"2305.13175","title":"Discovering Universal Geometry in Embeddings with ICA","created":"2023-05-22","cited_by_count":19,"area":null},{"id":"2107.12270","title":"Adaptive Hierarchical Graph Reasoning with Semantic Coherence for Video-and-Language Inference","created":"2021-07-26","cited_by_count":18,"area":null},{"id":"2204.09105","title":"An improved central limit theorem and fast convergence rates for entropic transportation costs","created":"2022-04-19","cited_by_count":18,"area":null},{"id":"2102.05912","title":"On Transportation of Mini-batches: A Hierarchical Approach","created":"2021-02-11","cited_by_count":16,"area":null},{"id":"2305.04034","title":"Wasserstein-Fisher-Rao Embedding: Logical Query Embeddings with Local Comparison and Global Transport","created":"2023-05-06","cited_by_count":16,"area":null},{"id":"2406.00288","title":"Neural Optimal Transport with Lagrangian Costs","created":"2024-06-01","cited_by_count":16,"area":null},{"id":"2503.24129","title":"It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data","created":"2025-03-31","cited_by_count":14,"area":null},{"id":"2108.10961","title":"Entropic Gromov-Wasserstein between Gaussian Distributions","created":"2021-08-24","cited_by_count":12,"area":null},{"id":"2402.02239","title":"Distributional Reduction: Unifying Dimensionality Reduction and Clustering with Gromov-Wasserstein","created":"2024-02-03","cited_by_count":12,"area":null},{"id":"2408.08233","title":"The Z-Gromov-Wasserstein Distance","created":"2024-08-15","cited_by_count":12,"area":null},{"id":"2106.02484","title":"NeuraCrypt: Hiding Private Health Data via Random Neural Networks for Public Training","created":"2021-06-04","cited_by_count":11,"area":null},{"id":"2107.06876","title":"Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More","created":"2021-07-14","cited_by_count":11,"area":null},{"id":"2205.13573","title":"Efficient Approximation of Gromov-Wasserstein Distance Using Importance Sparsification","created":"2022-05-26","cited_by_count":11,"area":null},{"id":"2210.03164","title":"InfoOT: Information Maximizing Optimal Transport","created":"2022-10-06","cited_by_count":9,"area":null},{"id":"2311.00915","title":"Task-Agnostic Low-Rank Adapters for Unseen English Dialects","created":"2023-11-02","cited_by_count":9,"area":null},{"id":"2409.16538","title":"Source-Free Domain Adaptation for YOLO Object Detection","created":"2024-09-25","cited_by_count":9,"area":null},{"id":"2103.00902","title":"Manifold optimization for non-linear optimal transport problems","created":"2021-03-01","cited_by_count":8,"area":null},{"id":"2201.12219","title":"Towards a Broad Coverage Named Entity Resource: A Data-Efficient Approach for Many Diverse Languages","created":"2022-01-28","cited_by_count":8,"area":null},{"id":"2201.12933","title":"Riemannian block SPD coupling manifold and its application to optimal transport","created":"2022-01-30","cited_by_count":7,"area":null},{"id":"2210.05098","title":"IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces","created":"2022-10-11","cited_by_count":7,"area":null},{"id":"2307.09057","title":"Globally solving the Gromov-Wasserstein problem for point clouds in low dimensional Euclidean spaces","created":"2023-07-18","cited_by_count":7,"area":null},{"id":"2405.03664","title":"A New Robust Partial $p$-Wasserstein-Based Metric for Comparing Distributions","created":"2024-05-06","cited_by_count":7,"area":null},{"id":"2104.04916","title":"Cross-Lingual Word Embedding Refinement by $\\ell_{1}$ Norm Optimisation","created":"2021-04-11","cited_by_count":6,"area":null},{"id":"2202.00808","title":"Gromov-Wasserstein Discrepancy with Local Differential Privacy for Distributed Structural Graphs","created":"2022-02-01","cited_by_count":6,"area":null},{"id":"2205.14923","title":"Unbalanced CO-Optimal Transport","created":"2022-05-30","cited_by_count":6,"area":null},{"id":"2210.14378","title":"Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport","created":"2022-10-25","cited_by_count":6,"area":null},{"id":"2212.02468","title":"Quantized Wasserstein Procrustes Alignment of Word Embedding Spaces","created":"2022-12-05","cited_by_count":6,"area":null},{"id":"2302.04610","title":"Outlier-Robust Gromov-Wasserstein for Graph Data","created":"2023-02-09","cited_by_count":6,"area":null},{"id":"2303.05978","title":"Uncovering Challenges of Solving the Continuous Gromov-Wasserstein Problem","created":"2023-03-10","cited_by_count":6,"area":null},{"id":"2304.00199","title":"Applications of No-Collision Transportation Maps in Manifold Learning","created":"2023-04-01","cited_by_count":6,"area":null},{"id":"2603.02237","title":"Concept Heterogeneity-aware Representation Steering","created":"2026-02-13","cited_by_count":6,"area":"mechinterp"},{"id":"2111.11328","title":"Cycle Consistent Probability Divergences Across Different Spaces","created":"2021-11-22","cited_by_count":5,"area":null},{"id":"2206.00238","title":"Transferable Reward Learning by Dynamics-Agnostic Discriminator Ensemble","created":"2022-06-01","cited_by_count":5,"area":"offlinerl"},{"id":"2301.11447","title":"Personalised Federated Learning On Heterogeneous Feature Spaces","created":"2023-01-26","cited_by_count":5,"area":null},{"id":"2406.04914","title":"Submodular Framework for Structured-Sparse Optimal Transport","created":"2024-06-07","cited_by_count":5,"area":null},{"id":"2406.10984","title":"Revisiting Cosine Similarity via Normalized ICA-transformed Embeddings","created":"2024-06-16","cited_by_count":5,"area":null},{"id":"2408.00981","title":"Cross-domain Named Entity Recognition via Graph Matching","created":"2024-08-02","cited_by_count":5,"area":null},{"id":"2410.21107","title":"Tree-Wasserstein Distance for High Dimensional Data with a Latent Feature Hierarchy","created":"2024-10-28","cited_by_count":5,"area":null},{"id":"2303.02241","title":"Domain adaptation using optimal transport for invariant learning using histopathology datasets","created":"2023-03-03","cited_by_count":4,"area":null},{"id":"2310.11256","title":"Gromov-Wasserstein-like Distances in the Gaussian Mixture Models Space","created":"2023-10-17","cited_by_count":4,"area":null},{"id":"2404.18773","title":"A Universal Metric of Dataset Similarity for Cross-silo Federated Learning","created":"2024-04-29","cited_by_count":4,"area":null},{"id":"2510.02348","title":"mini-vec2vec: Scaling Universal Geometry Alignment with Linear Transformations","created":"2025-09-27","cited_by_count":4,"area":null},{"id":"2201.11999","title":"Dual Learning Music Composition and Dance Choreography","created":"2022-01-28","cited_by_count":3,"area":null},{"id":"2203.08149","title":"MoReL: Multi-omics Relational Learning","created":"2022-03-15","cited_by_count":3,"area":null},{"id":"2205.05838","title":"Orthogonal Gromov-Wasserstein Discrepancy with Efficient Lower Bound","created":"2022-05-12","cited_by_count":3,"area":null},{"id":"2309.04158","title":"Context-Aware Prompt Tuning for Vision-Language Model with Dual-Alignment","created":"2023-09-08","cited_by_count":3,"area":"mllm"},{"id":"2310.13068","title":"GARI: Graph Attention for Relative Isomorphism of Arabic Word Embeddings","created":"2023-10-19","cited_by_count":3,"area":null},{"id":"2311.01375","title":"Monotone Generative Modeling via a Gromov-Monge Embedding","created":"2023-11-02","cited_by_count":3,"area":null},{"id":"2405.14532","title":"Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem","created":"2024-05-23","cited_by_count":3,"area":null},{"id":"2409.10085","title":"A Riemannian Approach to Ground Metric Learning for Optimal Transport","created":"2024-09-16","cited_by_count":3,"area":null},{"id":"2511.01202","title":"Forget BIT, It is All about TOKEN: Towards Semantic Information Theory for LLMs","created":"2025-11-03","cited_by_count":3,"area":null},{"id":"2101.03196","title":"Sketching Merge Trees for Scientific Data Visualization","created":"2021-01-08","cited_by_count":2,"area":null},{"id":"2105.12297","title":"Word Embedding Transformation for Robust Unsupervised Bilingual Lexicon Induction","created":"2021-05-26","cited_by_count":2,"area":null},{"id":"2106.07106","title":"Alignment and Comparison of Directed Networks via Transition Couplings of Random Walks","created":"2021-06-13","cited_by_count":2,"area":null},{"id":"2109.12640","title":"An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces","created":"2021-09-26","cited_by_count":2,"area":null},{"id":"2112.01806","title":"Music-to-Dance Generation with Optimal Transport","created":"2021-12-03","cited_by_count":2,"area":null},{"id":"2203.05744","title":"Semi-constraint Optimal Transport for Entity Alignment with Dangling Cases","created":"2022-03-11","cited_by_count":2,"area":null},{"id":"2209.02905","title":"A Data-dependent Approach for High Dimensional (Robust) Wasserstein Alignment","created":"2022-09-07","cited_by_count":2,"area":null},{"id":"2305.07500","title":"Learning representations that are closed-form Monge mapping optimal with application to domain adaptation","created":"2023-05-12","cited_by_count":2,"area":null},{"id":"2307.04096","title":"Optimal Transport Posterior Alignment for Cross-lingual Semantic Parsing","created":"2023-07-09","cited_by_count":2,"area":null},{"id":"2310.00672","title":"GeRA: Label-Efficient Geometrically Regularized Alignment","created":"2023-10-01","cited_by_count":2,"area":null},{"id":"2310.13995","title":"On Bilingual Lexicon Induction with Large Language Models","created":"2023-10-21","cited_by_count":2,"area":null},{"id":"2404.08970","title":"Fast Gradient Computation for Gromov-Wasserstein Distance","created":"2024-04-13","cited_by_count":2,"area":null},{"id":"2406.13507","title":"Scalable unsupervised alignment of general metric and non-metric structures","created":"2024-06-19","cited_by_count":2,"area":null},{"id":"2407.10495","title":"Improving Hyperbolic Representations via Gromov-Wasserstein Regularization","created":"2024-07-15","cited_by_count":2,"area":null},{"id":"2503.21538","title":"Formation Shape Control using the Gromov-Wasserstein Metric","created":"2025-03-27","cited_by_count":2,"area":null},{"id":"2504.02618","title":"Variational Online Mirror Descent for Robust Learning in Schr\\\"odinger Bridge","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2506.00573","title":"Neural Estimation for Scaling Entropic Multimarginal Optimal Transport","created":"2025-05-31","cited_by_count":2,"area":null},{"id":"2508.10745","title":"Agentic Design Review System","created":"2025-08-14","cited_by_count":2,"area":"agents"},{"id":"2602.01427","title":"Robust Generalization with Adaptive Optimal Transport Priors for Decision-Focused Learning","created":"2026-02-01","cited_by_count":2,"area":null},{"id":"2106.02542","title":"Heterogeneous Wasserstein Discrepancy for Incomparable Distributions","created":"2021-06-04","cited_by_count":1,"area":null},{"id":"2107.13494","title":"Limit Distribution Theory for the Smooth 1-Wasserstein Distance with Applications","created":"2021-07-28","cited_by_count":1,"area":null},{"id":"2110.02554","title":"A Regularized Wasserstein Framework for Graph Kernels","created":"2021-10-06","cited_by_count":1,"area":null},{"id":"2205.15713","title":"Don't Forget Cheap Training Signals Before Building Unsupervised Bilingual Word Embeddings","created":"2022-05-31","cited_by_count":1,"area":null},{"id":"2209.00232","title":"Hybrid Gromov-Wasserstein Embedding for Capsule Learning","created":"2022-09-01","cited_by_count":1,"area":null},{"id":"2303.13102","title":"Keypoint-Guided Optimal Transport: Models, Algorithms, and Applications","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2305.03565","title":"The geometry of financial institutions -- Wasserstein clustering of financial data","created":"2023-05-05","cited_by_count":1,"area":null},{"id":"2306.03218","title":"Optimal transport for automatic alignment of untargeted metabolomic data","created":"2023-06-05","cited_by_count":1,"area":null},{"id":"2310.17558","title":"Towards Matching Phones and Speech Representations","created":"2023-10-26","cited_by_count":1,"area":null},{"id":"2311.13595","title":"Covariance alignment: from maximum likelihood estimation to Gromov-Wasserstein","created":"2023-11-22","cited_by_count":1,"area":null},{"id":"2312.12641","title":"Robust Point Matching with Distance Profiles","created":"2023-12-19","cited_by_count":1,"area":null},{"id":"2405.13153","title":"Max-sliced Wasserstein concentration and uniform ratio bounds of empirical measures on RKHS","created":"2024-05-21","cited_by_count":1,"area":null},{"id":"2406.14183","title":"Latent Functional Maps: a spectral framework for representation alignment","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2410.16669","title":"Linear Partial Gromov-Wasserstein Embedding","created":"2024-10-22","cited_by_count":1,"area":null},{"id":"2506.21507","title":"Robust Alignment via Partial Gromov-Wasserstein Distances","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2605.09485","title":"SEMASIA: A Large-Scale Dataset of Semantically Structured Latent Representations","created":"2026-05-10","cited_by_count":1,"area":null}],"next_cursor":"100"}