{"total":29,"rows":[{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471,"area":null},{"id":"2210.08277","title":"Deep Differentiable Logic Gate Networks","created":"2022-10-15","cited_by_count":67,"area":null},{"id":"2111.08851","title":"Deep Neural Networks for Rank-Consistent Ordinal Regression Based On Conditional Probabilities","created":"2021-11-17","cited_by_count":59,"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":"2203.09630","title":"Monotonic Differentiable Sorting Networks","created":"2022-03-17","cited_by_count":25,"area":null},{"id":"2206.07290","title":"Differentiable Top-k Classification Learning","created":"2022-06-15","cited_by_count":21,"area":null},{"id":"2408.11054","title":"Near, far: Patch-ordering enhances vision foundation models' scene understanding","created":"2024-08-20","cited_by_count":15,"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":"2406.06246","title":"Data-Efficient Learning with Neural Programs","created":"2024-06-10","cited_by_count":7,"area":null},{"id":"2305.19999","title":"Beam Tree Recursive Cells","created":"2023-05-31","cited_by_count":6,"area":null},{"id":"2307.04049","title":"Parallel Algorithms Align with Neural Execution","created":"2023-07-08","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":"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":"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":"2202.13197","title":"Relational Surrogate Loss Learning","created":"2022-02-26","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":"2603.08824","title":"SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradients","created":"2026-03-09","cited_by_count":2,"area":null},{"id":"2304.13594","title":"Diffsurv: Differentiable sorting for censored time-to-event data","created":"2023-04-26","cited_by_count":0,"area":null},{"id":"2408.05391","title":"SAMSA: Efficient Transformer for Many Data Modalities","created":"2024-08-10","cited_by_count":0,"area":null},{"id":"2408.13825","title":"RoCP-GNN: Robust Conformal Prediction for Graph Neural Networks in Node-Classification","created":"2024-08-25","cited_by_count":0,"area":null},{"id":"2506.19104","title":"On the algorithmic construction of deep ReLU networks","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2512.02704","title":"Conformal Correction for Efficiency May be at Odds with Entropy","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2512.22587","title":"Structural Incompatibility of Differentiable Sorting and Within-Vector Rank Normalization","created":"2025-12-27","cited_by_count":0,"area":null},{"id":"2604.01228","title":"Logic-Gated Time-Shared Feedforward Networks for Alternating Finite Automata: Exact Simulation and Learnability","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2608.04057","title":"LaPrune: Controllable Differentiable Sparsity at Million Scale","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.06912","title":"Fast LapSum: Exact Differentiable Top-$k$ at Million Scale","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.01807","title":"SPD: Single Pass Decoding for Generative Reranking","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}