{"total":113,"rows":[{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471,"area":null},{"id":"2511.08544","title":"LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics","created":"2025-11-11","cited_by_count":254,"area":null},{"id":"2110.09192","title":"Learning Optimal Conformal Classifiers","created":"2021-10-18","cited_by_count":112,"area":null},{"id":"2211.06489","title":"Equivariance with Learned Canonicalization Functions","created":"2022-11-11","cited_by_count":109,"area":null},{"id":"2201.12324","title":"Optimal Transport Tools (OTT): A JAX Toolbox for all things Wasserstein","created":"2022-01-28","cited_by_count":101,"area":null},{"id":"2412.15287","title":"Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models","created":"2024-12-18","cited_by_count":89,"area":"lr"},{"id":"2505.15201","title":"Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems","created":"2025-05-21","cited_by_count":87,"area":"deeprl"},{"id":"2104.03059","title":"Differentiable Patch Selection for Image Recognition","created":"2021-04-07","cited_by_count":68,"area":null},{"id":"2210.08277","title":"Deep Differentiable Logic Gate Networks","created":"2022-10-15","cited_by_count":67,"area":null},{"id":"2103.17202","title":"GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection","created":"2021-03-31","cited_by_count":66,"area":null},{"id":"2205.05878","title":"Training Uncertainty-Aware Classifiers with Conformalized Deep Learning","created":"2022-05-12","cited_by_count":64,"area":null},{"id":"2305.17328","title":"Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers","created":"2023-05-27","cited_by_count":62,"area":"inference"},{"id":"2111.11591","title":"Efficient Video Transformers with Spatial-Temporal Token Selection","created":"2021-11-23","cited_by_count":59,"area":null},{"id":"2205.15236","title":"RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression","created":"2022-05-30","cited_by_count":52,"area":null},{"id":"2510.14510","title":"Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective","created":"2025-10-16","cited_by_count":39,"area":null},{"id":"2210.01941","title":"SIMPLE: A Gradient Estimator for $k$-Subset Sampling","created":"2022-10-04","cited_by_count":34,"area":null},{"id":"2406.09196","title":"Adaptive Slot Attention: Object Discovery with Dynamic Slot Number","created":"2024-06-13","cited_by_count":34,"area":null},{"id":"2105.04019","title":"Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision","created":"2021-05-09","cited_by_count":31,"area":null},{"id":"2205.06688","title":"A Unified Framework for Implicit Sinkhorn Differentiation","created":"2022-05-13","cited_by_count":28,"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":"2306.02738","title":"A Large-Scale Study of Probabilistic Calibration in Neural Network Regression","created":"2023-06-05","cited_by_count":27,"area":null},{"id":"2404.19651","title":"Provably Robust Conformal Prediction with Improved Efficiency","created":"2024-04-30","cited_by_count":27,"area":null},{"id":"2302.01425","title":"Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective","created":"2023-02-02","cited_by_count":26,"area":null},{"id":"2406.05882","title":"Distributional Preference Alignment of LLMs via Optimal Transport","created":"2024-06-09","cited_by_count":26,"area":"alignment"},{"id":"2203.09630","title":"Monotonic Differentiable Sorting Networks","created":"2022-03-17","cited_by_count":25,"area":null},{"id":"2201.00730","title":"Faster Unbalanced Optimal Transport: Translation invariant Sinkhorn and 1-D Frank-Wolfe","created":"2022-01-03","cited_by_count":22,"area":null},{"id":"2502.03609","title":"Multivariate Conformal Prediction using Optimal Transport","created":"2025-02-05","cited_by_count":22,"area":null},{"id":"2110.05651","title":"Learning with Algorithmic Supervision via Continuous Relaxations","created":"2021-10-11","cited_by_count":21,"area":null},{"id":"2206.07290","title":"Differentiable Top-k Classification Learning","created":"2022-06-15","cited_by_count":21,"area":null},{"id":"2405.02140","title":"An Information Theoretic Perspective on Conformal Prediction","created":"2024-05-03","cited_by_count":21,"area":null},{"id":"2106.03257","title":"Structured Reordering for Modeling Latent Alignments in Sequence Transduction","created":"2021-06-06","cited_by_count":17,"area":null},{"id":"2210.03067","title":"Few-Shot Calibration of Set Predictors via Meta-Learned Cross-Validation-Based Conformal Prediction","created":"2022-10-06","cited_by_count":17,"area":null},{"id":"2407.13917","title":"LinSATNet: The Positive Linear Satisfiability Neural Networks","created":"2024-07-18","cited_by_count":16,"area":null},{"id":"2306.00344","title":"BOtied: Multi-objective Bayesian optimization with tied multivariate ranks","created":"2023-06-01","cited_by_count":15,"area":null},{"id":"2103.09879","title":"Self-Supervised Learning of Audio Representations from Permutations with Differentiable Ranking","created":"2021-03-17","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":"2206.07630","title":"Rethinking Initialization of the Sinkhorn Algorithm","created":"2022-06-15","cited_by_count":14,"area":null},{"id":"2204.06521","title":"Optimizing generalized Gini indices for fairness in rankings","created":"2022-04-02","cited_by_count":13,"area":null},{"id":"2301.02009","title":"Learning by Sorting: Self-supervised Learning with Group Ordering Constraints","created":"2023-01-05","cited_by_count":13,"area":null},{"id":"2503.06242","title":"LapSum -- One Method to Differentiate Them All: Ranking, Sorting and Top-k Selection","created":"2025-03-08","cited_by_count":13,"area":null},{"id":"2104.14547","title":"NURBS-Diff: A Differentiable Programming Module for NURBS","created":"2021-04-29","cited_by_count":11,"area":null},{"id":"2411.01696","title":"Conformal Risk Minimization with Variance Reduction","created":"2024-11-03","cited_by_count":11,"area":null},{"id":"2106.03188","title":"Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach","created":"2021-06-06","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":"2502.07962","title":"ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport Plans","created":"2025-02-11","cited_by_count":10,"area":null},{"id":"2206.12116","title":"Approximating 1-Wasserstein Distance with Trees","created":"2022-06-24","cited_by_count":9,"area":null},{"id":"2207.12717","title":"The derivatives of Sinkhorn-Knopp converge","created":"2022-07-26","cited_by_count":9,"area":null},{"id":"2103.12476","title":"Differentiable Agent-Based Simulation for Gradient-Guided Simulation-Based Optimization","created":"2021-03-23","cited_by_count":8,"area":null},{"id":"2205.14107","title":"Spartan: Differentiable Sparsity via Regularized Transportation","created":"2022-05-27","cited_by_count":8,"area":null},{"id":"2505.00917","title":"Multivariate Conformal Selection","created":"2025-05-01","cited_by_count":8,"area":"alignment"},{"id":"2409.17500","title":"GLinSAT: The General Linear Satisfiability Neural Network Layer By Accelerated Gradient Descent","created":"2024-09-26","cited_by_count":7,"area":null},{"id":"2410.09408","title":"C-Adapter: Adapting Deep Classifiers for Efficient Conformal Prediction Sets","created":"2024-10-12","cited_by_count":7,"area":null},{"id":"2103.09656","title":"Set-to-Sequence Methods in Machine Learning: a Review","created":"2021-03-17","cited_by_count":6,"area":null},{"id":"2204.13001","title":"Relevance-based Margin for Contrastively-trained Video Retrieval Models","created":"2022-04-27","cited_by_count":6,"area":null},{"id":"2305.19999","title":"Beam Tree Recursive Cells","created":"2023-05-31","cited_by_count":6,"area":null},{"id":"2310.10462","title":"Adaptive Neural Ranking Framework: Toward Maximized Business Goal for Cascade Ranking Systems","created":"2023-10-16","cited_by_count":6,"area":null},{"id":"2312.04658","title":"PAC-Bayes Generalization Certificates for Learned Inductive Conformal Prediction","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2405.20082","title":"Segment, Shuffle, and Stitch: A Simple Layer for Improving Time-Series Representations","created":"2024-05-30","cited_by_count":6,"area":null},{"id":"2410.02942","title":"SymmetricDiffusers: Learning Discrete Diffusion on Finite Symmetric Groups","created":"2024-10-03","cited_by_count":6,"area":"diffusion"},{"id":"2404.16828","title":"Made to Order: Discovering monotonic temporal changes via self-supervised video ordering","created":"2024-04-25","cited_by_count":5,"area":null},{"id":"2407.06141","title":"CHAMP: Conformalized 3D Human Multi-Hypothesis Pose Estimators","created":"2024-05-27","cited_by_count":5,"area":"diffusion"},{"id":"2110.01532","title":"Differentiable Spline Approximations","created":"2021-10-04","cited_by_count":4,"area":null},{"id":"2201.03528","title":"Permuted and Unlinked Monotone Regression in $\\mathbb{R}^d$: an approach based on mixture modeling and optimal transport","created":"2022-01-10","cited_by_count":4,"area":null},{"id":"2310.07174","title":"Generalized Neural Sorting Networks with Error-Free Differentiable Swap Functions","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2410.08125","title":"Generalizing Stochastic Smoothing for Differentiation and Gradient Estimation","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2606.17952","title":"SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs","created":"2026-06-16","cited_by_count":4,"area":"moe"},{"id":"2302.07964","title":"On Rank Energy Statistics via Optimal Transport: Continuity, Convergence, and Change Point Detection","created":"2023-02-15","cited_by_count":3,"area":null},{"id":"2305.07504","title":"Calibration-Aware Bayesian Learning","created":"2023-05-12","cited_by_count":3,"area":null},{"id":"2305.16841","title":"Differentiable Random Partition Models","created":"2023-05-26","cited_by_count":3,"area":null},{"id":"2305.18483","title":"Bringing regularized optimal transport to lightspeed: a splitting method adapted for GPUs","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2311.11934","title":"Estimation of entropy-regularized optimal transport maps between non-compactly supported measures","created":"2023-11-20","cited_by_count":3,"area":null},{"id":"2401.11354","title":"Squared Wasserstein-2 Distance for Efficient Reconstruction of Stochastic Differential Equations","created":"2024-01-21","cited_by_count":3,"area":null},{"id":"2501.10789","title":"CS-Net:Contribution-based Sampling Network for Point Cloud Simplification","created":"2025-01-18","cited_by_count":3,"area":null},{"id":"2509.25473","title":"Conformal Prediction for Signal Temporal Logic Inference","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2101.09039","title":"Projected Statistical Methods for Distributional Data on the Real Line with the Wasserstein Metric","created":"2021-01-22","cited_by_count":2,"area":null},{"id":"2203.12873","title":"Weakly-Supervised End-to-End CAD Retrieval to Scan Objects","created":"2022-03-24","cited_by_count":2,"area":null},{"id":"2304.00961","title":"Self-Ordering Point Clouds","created":"2023-04-03","cited_by_count":2,"area":null},{"id":"2304.08272","title":"About latent roles in forecasting players in team sports","created":"2023-04-17","cited_by_count":2,"area":null},{"id":"2404.17483","title":"Differentiable Pareto-Smoothed Weighting for High-Dimensional Heterogeneous Treatment Effect Estimation","created":"2024-04-26","cited_by_count":2,"area":null},{"id":"2406.08399","title":"Differentiable Cost-Parameterized Monge Map Estimators","created":"2024-06-12","cited_by_count":2,"area":null},{"id":"2410.19055","title":"Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2503.09492","title":"Learning Cascade Ranking as One Network","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2505.15661","title":"Deep greedy unfolding: Sorting out argsorting in greedy sparse recovery algorithms","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2506.17197","title":"Schr\\\"odinger Bridge Matching for Tree-Structured Costs and Entropic Wasserstein Barycentres","created":"2025-06-20","cited_by_count":2,"area":null},{"id":"2603.08824","title":"SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradients","created":"2026-03-09","cited_by_count":2,"area":null},{"id":"2304.00049","title":"Ranking Regularization for Critical Rare Classes: Minimizing False Positives at a High True Positive Rate","created":"2023-03-31","cited_by_count":1,"area":null},{"id":"2305.12396","title":"Joint Feature and Differentiable $ k $-NN Graph Learning using Dirichlet Energy","created":"2023-05-21","cited_by_count":1,"area":null},{"id":"2308.09228","title":"Generalized Sum Pooling for Metric Learning","created":"2023-08-18","cited_by_count":1,"area":null},{"id":"2507.09711","title":"Phase transition of the Sinkhorn-Knopp algorithm","created":"2025-07-13","cited_by_count":1,"area":null},{"id":"2601.21775","title":"Differentiable Knapsack and Top-k Operators via Dynamic Programming","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2603.26940","title":"Static and Dynamic Approaches to Computing Barycenters of Probability Measures on Graphs","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2305.00319","title":"Learning to Re-rank with Constrained Meta-Optimal Transport","created":"2023-04-29","cited_by_count":0,"area":null},{"id":"2305.07315","title":"$\\partial\\mathbb{B}$ nets: learning discrete functions by gradient descent","created":"2023-05-12","cited_by_count":0,"area":null},{"id":"2306.04184","title":"StructuredMesh: 3D Structured Optimization of Fa\\c{c}ade Components on Photogrammetric Mesh Models using Binary Integer Programming","created":"2023-06-07","cited_by_count":0,"area":null},{"id":"2410.17111","title":"Permutation Picture of Graph Combinatorial Optimization Problems","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2411.01956","title":"EXAGREE: Mitigating Explanation Disagreement with Stakeholder-Aligned Models","created":"2024-11-04","cited_by_count":0,"area":null},{"id":"2411.03253","title":"Discovering Data Structures: Nearest Neighbor Search and Beyond","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2503.24204","title":"Many-to-Many Matching via Sparsity Controlled Optimal Transport","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2505.24664","title":"Learning Distributions over Permutations and Rankings with Factorized Representations","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2509.12081","title":"Deceptive Risk Minimization: Out-of-Distribution Generalization by Deceiving Distribution Shift Detectors","created":"2025-09-15","cited_by_count":0,"area":null}],"next_cursor":"100"}