{"total":26,"rows":[{"id":"2212.12042","title":"Re-basin via implicit Sinkhorn differentiation","created":"2022-12-22","cited_by_count":62,"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":"2306.05272","title":"Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models","created":"2023-06-08","cited_by_count":22,"area":null},{"id":"2506.22712","title":"Generalized Linear Mode Connectivity for Transformers","created":"2025-06-28","cited_by_count":16,"area":null},{"id":"2301.01805","title":"Unsupervised Manifold Linearizing and Clustering","created":"2023-01-04","cited_by_count":12,"area":null},{"id":"2309.13167","title":"Flow Factorized Representation Learning","created":"2023-09-22","cited_by_count":11,"area":null},{"id":"2310.01362","title":"Robot Fleet Learning via Policy Merging","created":"2023-10-02","cited_by_count":11,"area":null},{"id":"2602.03067","title":"FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPU","created":"2026-02-03","cited_by_count":11,"area":null},{"id":"2307.08483","title":"Differentiable Transportation Pruning","created":"2023-07-17","cited_by_count":10,"area":null},{"id":"2207.12717","title":"The derivatives of Sinkhorn-Knopp converge","created":"2022-07-26","cited_by_count":9,"area":null},{"id":"2311.07633","title":"Benchmarking PtO and PnO Methods in the Predictive Combinatorial Optimization Regime","created":"2023-11-13","cited_by_count":8,"area":null},{"id":"2505.22109","title":"The quest for the GRAph Level autoEncoder (GRALE)","created":"2025-05-28","cited_by_count":8,"area":null},{"id":"2210.06574","title":"Gaussian Processes on Distributions based on Regularized Optimal Transport","created":"2022-10-12","cited_by_count":6,"area":null},{"id":"2502.20141","title":"Your contrastive learning problem is secretly a distribution alignment problem","created":"2025-02-27","cited_by_count":6,"area":null},{"id":"2602.18308","title":"JPmHC Dynamical Isometry via Orthogonal Hyper-Connections","created":"2026-02-20","cited_by_count":5,"area":null},{"id":"2602.23353","title":"SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2307.08930","title":"Unsupervised Deep Graph Matching Based on Cycle Consistency","created":"2023-07-18","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":"2608.16884","title":"Improving the matrix multiplication exponent with modern optimization and AlphaEvolve","created":"2026-08-17","cited_by_count":2,"area":null},{"id":"2502.04409","title":"Learning low-dimensional representations of ensemble forecast fields using autoencoder-based methods","created":"2025-02-06","cited_by_count":1,"area":null},{"id":"2601.23039","title":"Avoiding Premature Collapse: Adaptive Annealing for Entropy-Regularized Structural Inference","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2211.14448","title":"How to Backpropagate through Hungarian in Your DETR?","created":"2022-11-12","cited_by_count":0,"area":null},{"id":"2601.07144","title":"Optimal Transport under Group Fairness Constraints","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2602.22052","title":"AutoSew: A Geometric Approach to Stitching Prediction with Graph Neural Networks","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2609.07954","title":"Support Topology and Gradient Mixing in Sinkhorn Layers","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.23242","title":"Proximal Residual Value Functions for Consistent Planning and Real-Time Execution","created":"2026-09-19","cited_by_count":0,"area":null}],"next_cursor":null}