{"total":314,"rows":[{"id":"2302.00482","title":"Improving and generalizing flow-based generative models with minibatch optimal transport","created":"2023-02-01","cited_by_count":879,"area":"diffusion"},{"id":"2106.01357","title":"Diffusion Schr\\\"odinger Bridge with Applications to Score-Based Generative Modeling","created":"2021-06-01","cited_by_count":602,"area":"diffusion"},{"id":"2304.14772","title":"Multisample Flow Matching: Straightening Flows with Minibatch Couplings","created":"2023-04-28","cited_by_count":278,"area":"diffusion"},{"id":"2310.02391","title":"SE(3)-Stochastic Flow Matching for Protein Backbone Generation","created":"2023-10-03","cited_by_count":150,"area":"diffusion"},{"id":"2103.03606","title":"Unbalanced minibatch Optimal Transport; applications to Domain Adaptation","created":"2021-03-05","cited_by_count":125,"area":null},{"id":"2109.12004","title":"Entropic estimation of optimal transport maps","created":"2021-09-24","cited_by_count":90,"area":null},{"id":"2307.03672","title":"Simulation-free Schr\\\"odinger bridges via score and flow matching","created":"2023-07-07","cited_by_count":83,"area":"diffusion"},{"id":"2110.02999","title":"Generative Modeling with Optimal Transport Maps","created":"2021-10-06","cited_by_count":82,"area":null},{"id":"2405.14664","title":"Fisher Flow Matching for Generative Modeling over Discrete Data","created":"2024-05-23","cited_by_count":72,"area":"diffusion"},{"id":"2305.00054","title":"LAVA: Data Valuation without Pre-Specified Learning Algorithms","created":"2023-04-28","cited_by_count":69,"area":null},{"id":"2306.16156","title":"Recent Advances in Optimal Transport for Machine Learning","created":"2023-06-28","cited_by_count":66,"area":null},{"id":"2101.01792","title":"Minibatch optimal transport distances; analysis and applications","created":"2021-01-05","cited_by_count":65,"area":null},{"id":"2309.09968","title":"Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees","created":"2023-09-18","cited_by_count":62,"area":null},{"id":"2302.03133","title":"Domain Adaptation for Time Series Under Feature and Label Shifts","created":"2023-02-06","cited_by_count":60,"area":null},{"id":"2102.07850","title":"Differentiable Particle Filtering via Entropy-Regularized Optimal Transport","created":"2021-02-15","cited_by_count":59,"area":null},{"id":"2106.00774","title":"Optimizing Functionals on the Space of Probabilities with Input Convex Neural Networks","created":"2021-06-01","cited_by_count":53,"area":null},{"id":"2407.00224","title":"Multimodal Prototyping for cancer survival prediction","created":"2024-06-28","cited_by_count":47,"area":null},{"id":"2211.08775","title":"Unbalanced Optimal Transport, from Theory to Numerics","created":"2022-11-16","cited_by_count":46,"area":null},{"id":"2306.04217","title":"Effective Neural Topic Modeling with Embedding Clustering Regularization","created":"2023-06-07","cited_by_count":46,"area":null},{"id":"2106.08229","title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes","created":"2021-06-03","cited_by_count":43,"area":null},{"id":"2108.09645","title":"Improving Mini-batch Optimal Transport via Partial Transportation","created":"2021-08-22","cited_by_count":41,"area":null},{"id":"2106.03812","title":"Neural Monge Map estimation and its applications","created":"2021-06-07","cited_by_count":40,"area":null},{"id":"2109.11926","title":"Sinkhorn Distributionally Robust Optimization","created":"2021-09-24","cited_by_count":38,"area":null},{"id":"2307.02106","title":"SoK: Privacy-Preserving Data Synthesis","created":"2023-07-05","cited_by_count":38,"area":null},{"id":"2106.08929","title":"KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Support","created":"2021-06-16","cited_by_count":37,"area":null},{"id":"2403.18705","title":"Conditional Wasserstein Distances with Applications in Bayesian OT Flow Matching","created":"2024-03-27","cited_by_count":36,"area":"diffusion"},{"id":"2103.01678","title":"Wasserstein GANs Work Because They Fail (to Approximate the Wasserstein Distance)","created":"2021-03-02","cited_by_count":35,"area":null},{"id":"2106.01963","title":"A Survey on Optimal Transport for Machine Learning: Theory and Applications","created":"2021-06-03","cited_by_count":35,"area":null},{"id":"2405.17978","title":"FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model","created":"2024-05-28","cited_by_count":35,"area":null},{"id":"2103.15375","title":"AlignMixup: Improving Representations By Interpolating Aligned Features","created":"2021-03-29","cited_by_count":33,"area":null},{"id":"2405.02774","title":"Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs","created":"2024-05-05","cited_by_count":32,"area":null},{"id":"2302.10363","title":"Transformed Distribution Matching for Missing Value Imputation","created":"2023-02-20","cited_by_count":31,"area":null},{"id":"2402.04467","title":"DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systems","created":"2024-02-06","cited_by_count":30,"area":null},{"id":"2205.06688","title":"A Unified Framework for Implicit Sinkhorn Differentiation","created":"2022-05-13","cited_by_count":28,"area":null},{"id":"2206.05262","title":"Meta Optimal Transport","created":"2022-06-10","cited_by_count":28,"area":null},{"id":"2102.06857","title":"On Robust Optimal Transport: Computational Complexity and Barycenter Computation","created":"2021-02-13","cited_by_count":27,"area":null},{"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":"2603.12366","title":"Sinkhorn-Drifting Generative Models","created":"2026-03-12","cited_by_count":24,"area":null},{"id":"2605.11755","title":"One-Step Generative Modeling via Wasserstein Gradient Flows","created":"2026-05-12","cited_by_count":24,"area":"diffusion"},{"id":"2209.13570","title":"Hierarchical Sliced Wasserstein Distance","created":"2022-09-27","cited_by_count":23,"area":null},{"id":"2205.12365","title":"Low-rank Optimal Transport: Approximation, Statistics and Debiasing","created":"2022-05-24","cited_by_count":21,"area":null},{"id":"2210.04135","title":"VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment","created":"2022-10-09","cited_by_count":20,"area":"mllm"},{"id":"2212.03722","title":"Optimal transport map estimation in general function spaces","created":"2022-12-07","cited_by_count":20,"area":null},{"id":"2301.11302","title":"Minimax estimation of discontinuous optimal transport maps: The semi-discrete case","created":"2023-01-26","cited_by_count":20,"area":null},{"id":"2201.09366","title":"Optimal transport for causal discovery","created":"2022-01-23","cited_by_count":19,"area":null},{"id":"2310.17405","title":"Causal Modeling with Stationary Diffusions","created":"2023-10-26","cited_by_count":19,"area":null},{"id":"2405.06780","title":"Deep MMD Gradient Flow without adversarial training","created":"2024-05-10","cited_by_count":19,"area":null},{"id":"2102.12833","title":"Diffusion Earth Mover's Distance and Distribution Embeddings","created":"2021-02-25","cited_by_count":18,"area":null},{"id":"2107.01558","title":"Direct Measure Matching for Crowd Counting","created":"2021-07-04","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":"2401.14113","title":"On the Affinity, Rationality, and Diversity of Hierarchical Topic Modeling","created":"2024-01-25","cited_by_count":18,"area":null},{"id":"2111.12187","title":"Input Convex Gradient Networks","created":"2021-11-23","cited_by_count":17,"area":null},{"id":"2203.13417","title":"Amortized Projection Optimization for Sliced Wasserstein Generative Models","created":"2022-03-25","cited_by_count":17,"area":null},{"id":"2210.08139","title":"Partial Identification of Treatment Effects with Implicit Generative Models","created":"2022-10-14","cited_by_count":17,"area":null},{"id":"2301.13737","title":"Self-Consistent Velocity Matching of Probability Flows","created":"2023-01-31","cited_by_count":17,"area":null},{"id":"2502.12456","title":"Not-So-Optimal Transport Flows for 3D Point Cloud Generation","created":"2025-02-18","cited_by_count":17,"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":"2202.03618","title":"On Unbalanced Optimal Transport: Gradient Methods, Sparsity and Approximation Error","created":"2022-02-08","cited_by_count":16,"area":null},{"id":"2209.06975","title":"Wasserstein $K$-means for clustering probability distributions","created":"2022-09-14","cited_by_count":16,"area":null},{"id":"2302.04065","title":"Monge, Bregman and Occam: Interpretable Optimal Transport in High-Dimensions with Feature-Sparse Maps","created":"2023-02-08","cited_by_count":16,"area":null},{"id":"2307.02460","title":"Performance Scaling via Optimal Transport: Enabling Data Selection from Partially Revealed Sources","created":"2023-07-05","cited_by_count":16,"area":null},{"id":"2307.02402","title":"Unbalanced Optimal Transport: A Unified Framework for Object Detection","created":"2023-07-05","cited_by_count":15,"area":null},{"id":"2402.17110","title":"Sinkhorn Distance Minimization for Knowledge Distillation","created":"2024-02-27","cited_by_count":15,"area":"distill"},{"id":"2106.02933","title":"k-Mixup Regularization for Deep Learning via Optimal Transport","created":"2021-06-05","cited_by_count":14,"area":null},{"id":"2106.07877","title":"Learning Revenue-Maximizing Auctions With Differentiable Matching","created":"2021-06-15","cited_by_count":14,"area":null},{"id":"2107.05680","title":"Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions","created":"2021-07-12","cited_by_count":14,"area":null},{"id":"2112.00423","title":"Controlling Wasserstein Distances by Kernel Norms with Application to Compressive Statistical Learning","created":"2021-12-01","cited_by_count":14,"area":null},{"id":"2206.07630","title":"Rethinking Initialization of the Sinkhorn Algorithm","created":"2022-06-15","cited_by_count":14,"area":null},{"id":"2207.05510","title":"Transferability-Guided Cross-Domain Cross-Task Transfer Learning","created":"2022-07-12","cited_by_count":14,"area":null},{"id":"2209.01501","title":"Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributions","created":"2022-09-03","cited_by_count":14,"area":null},{"id":"2404.09411","title":"Wasserstein Wormhole: Scalable Optimal Transport Distance with Transformers","created":"2024-04-15","cited_by_count":14,"area":null},{"id":"2503.10679","title":"LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss","created":"2025-03-11","cited_by_count":14,"area":"mechinterp"},{"id":"2103.06263","title":"Semi-Discrete Optimal Transport: Hardness, Regularization and Numerical Solution","created":"2021-03-10","cited_by_count":13,"area":null},{"id":"2109.15044","title":"SPATE-GAN: Improved Generative Modeling of Dynamic Spatio-Temporal Patterns with an Autoregressive Embedding Loss","created":"2021-09-30","cited_by_count":13,"area":null},{"id":"2205.00504","title":"Domain Adaptation meets Individual Fairness. And they get along","created":"2022-05-01","cited_by_count":13,"area":null},{"id":"2301.11674","title":"Optimally-Weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference","created":"2023-01-27","cited_by_count":13,"area":null},{"id":"2302.13183","title":"On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds","created":"2023-02-25","cited_by_count":13,"area":null},{"id":"2108.10961","title":"Entropic Gromov-Wasserstein between Gaussian Distributions","created":"2021-08-24","cited_by_count":12,"area":null},{"id":"2202.03814","title":"Optimal Transport of Classifiers to Fairness","created":"2022-02-08","cited_by_count":12,"area":null},{"id":"2208.14995","title":"Discovering Conservation Laws using Optimal Transport and Manifold Learning","created":"2022-08-31","cited_by_count":12,"area":null},{"id":"2301.12874","title":"Extremal Domain Translation with Neural Optimal Transport","created":"2023-01-30","cited_by_count":12,"area":null},{"id":"2307.10352","title":"Properties of Discrete Sliced Wasserstein Losses","created":"2023-07-19","cited_by_count":12,"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":"2301.03749","title":"Markovian Sliced Wasserstein Distances: Beyond Independent Projections","created":"2023-01-10","cited_by_count":11,"area":null},{"id":"2401.12253","title":"Accelerating Sinkhorn Algorithm with Sparse Newton Iterations","created":"2024-01-20","cited_by_count":11,"area":null},{"id":"2102.02992","title":"Learning High Dimensional Wasserstein Geodesics","created":"2021-02-05","cited_by_count":10,"area":null},{"id":"2105.14403","title":"Re-evaluating Word Mover's Distance","created":"2021-05-30","cited_by_count":10,"area":null},{"id":"2109.14090","title":"Reversible Gromov-Monge Sampler for Simulation-Based Inference","created":"2021-09-28","cited_by_count":10,"area":null},{"id":"2205.11164","title":"Time-series Transformer Generative Adversarial Networks","created":"2022-05-23","cited_by_count":10,"area":null},{"id":"2303.11844","title":"Doubly Regularized Entropic Wasserstein Barycenters","created":"2023-03-21","cited_by_count":10,"area":null},{"id":"2307.08483","title":"Differentiable Transportation Pruning","created":"2023-07-17","cited_by_count":10,"area":null},{"id":"2307.14442","title":"Neural Schr\\\"{o}dinger Bridge with Sinkhorn Losses: Application to Data-driven Minimum Effort Control of Colloidal Self-assembly","created":"2023-07-26","cited_by_count":10,"area":null},{"id":"2405.10084","title":"Revisiting Deep Audio-Text Retrieval Through the Lens of Transportation","created":"2024-05-16","cited_by_count":10,"area":null},{"id":"2406.05061","title":"Progressive Entropic Optimal Transport Solvers","created":"2024-06-07","cited_by_count":10,"area":null},{"id":"2605.06797","title":"MIND: Monge Inception Distance for Generative Models Evaluation","created":"2026-05-07","cited_by_count":10,"area":null},{"id":"2106.07911","title":"Non-asymptotic convergence bounds for Wasserstein approximation using point clouds","created":"2021-06-15","cited_by_count":9,"area":null},{"id":"2112.15265","title":"Entropy Regularized Optimal Transport Independence Criterion","created":"2021-12-31","cited_by_count":9,"area":null},{"id":"2204.01612","title":"Neural Estimation of the Rate-Distortion Function With Applications to Operational Source Coding","created":"2022-04-04","cited_by_count":9,"area":null},{"id":"2205.15059","title":"Hilbert Curve Projection Distance for Distribution Comparison","created":"2022-05-30","cited_by_count":9,"area":null},{"id":"2206.12116","title":"Approximating 1-Wasserstein Distance with Trees","created":"2022-06-24","cited_by_count":9,"area":null}],"next_cursor":"100"}