{"total":103,"rows":[{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673,"area":null},{"id":"2110.11773","title":"Sinkformers: Transformers with Doubly Stochastic Attention","created":"2021-10-22","cited_by_count":138,"area":null},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136,"area":null},{"id":"2106.13679","title":"Shape registration in the time of transformers","created":"2021-06-25","cited_by_count":51,"area":null},{"id":"2111.00648","title":"Accurate Point Cloud Registration with Robust Optimal Transport","created":"2021-11-01","cited_by_count":38,"area":null},{"id":"2103.14608","title":"On UMAP's true loss function","created":"2021-03-26","cited_by_count":32,"area":null},{"id":"2102.09204","title":"Towards a mathematical theory of trajectory inference","created":"2021-02-18","cited_by_count":31,"area":null},{"id":"2206.01816","title":"From $t$-SNE to UMAP with contrastive learning","created":"2022-06-03","cited_by_count":28,"area":null},{"id":"2205.15449","title":"Posterior and Computational Uncertainty in Gaussian Processes","created":"2022-05-30","cited_by_count":24,"area":null},{"id":"2107.00243","title":"Preconditioning for Scalable Gaussian Process Hyperparameter Optimization","created":"2021-07-01","cited_by_count":23,"area":null},{"id":"2211.16199","title":"Latent Graph Inference using Product Manifolds","created":"2022-11-26","cited_by_count":23,"area":null},{"id":"2212.00768","title":"Simplifying and Understanding State Space Models with Diagonal Linear RNNs","created":"2022-12-01","cited_by_count":23,"area":null},{"id":"2102.08314","title":"Tighter Bounds on the Log Marginal Likelihood of Gaussian Process Regression Using Conjugate Gradients","created":"2021-02-16","cited_by_count":20,"area":null},{"id":"2204.04238","title":"Elastic shape analysis of surfaces with second-order Sobolev metrics: a comprehensive numerical framework","created":"2022-04-08","cited_by_count":19,"area":null},{"id":"2101.09458","title":"Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning","created":"2021-01-23","cited_by_count":14,"area":null},{"id":"2404.00330","title":"Memory-Scalable and Simplified Functional Map Learning","created":"2024-03-30","cited_by_count":14,"area":null},{"id":"2102.07951","title":"ResNet-LDDMM: Advancing the LDDMM Framework using Deep Residual Networks","created":"2021-02-16","cited_by_count":13,"area":null},{"id":"2107.02010","title":"Fast and Scalable Optimal Transport for Brain Tractograms","created":"2021-07-05","cited_by_count":12,"area":null},{"id":"2205.14977","title":"Fast Nonlinear Vector Quantile Regression","created":"2022-05-30","cited_by_count":12,"area":null},{"id":"2201.06314","title":"Efficient Hyperparameter Tuning for Large Scale Kernel Ridge Regression","created":"2022-01-17","cited_by_count":11,"area":null},{"id":"2310.15788","title":"qPOTS: Efficient batch multiobjective Bayesian optimization via Pareto optimal Thompson sampling","created":"2023-10-24","cited_by_count":11,"area":null},{"id":"2310.17137","title":"Large-Scale Gaussian Processes via Alternating Projection","created":"2023-10-26","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":"2207.06856","title":"Low-Precision Arithmetic for Fast Gaussian Processes","created":"2022-07-14","cited_by_count":10,"area":null},{"id":"2503.08305","title":"ELECTRA: A Cartesian Network for 3D Charge Density Prediction with Floating Orbitals","created":"2025-03-11","cited_by_count":10,"area":null},{"id":"2106.06695","title":"SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes","created":"2021-06-12","cited_by_count":9,"area":null},{"id":"2108.06317","title":"Towards Efficient Point Cloud Graph Neural Networks Through Architectural Simplification","created":"2021-08-13","cited_by_count":9,"area":null},{"id":"2411.07154","title":"Conditional simulation via entropic optimal transport: Toward non-parametric estimation of conditional Brenier maps","created":"2024-11-11","cited_by_count":9,"area":null},{"id":"2501.19183","title":"Position: Curvature Matrices Should Be Democratized via Linear Operators","created":"2025-01-31","cited_by_count":9,"area":null},{"id":"2204.05300","title":"Single-Photon Structured Light","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2207.12485","title":"3D Shape Sequence of Human Comparison and Classification using Current and Varifolds","created":"2022-07-25","cited_by_count":8,"area":null},{"id":"2401.08260","title":"Fast Kernel Summation in High Dimensions via Slicing and Fourier Transforms","created":"2024-01-16","cited_by_count":8,"area":null},{"id":"2307.08507","title":"Efficient and Accurate Optimal Transport with Mirror Descent and Conjugate Gradients","created":"2023-07-17","cited_by_count":7,"area":null},{"id":"2309.03060","title":"CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra","created":"2023-09-06","cited_by_count":7,"area":null},{"id":"2401.04305","title":"Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions","created":"2024-01-09","cited_by_count":7,"area":null},{"id":"2410.01316","title":"Fast Summation of Radial Kernels via QMC Slicing","created":"2024-10-02","cited_by_count":7,"area":null},{"id":"2204.14057","title":"Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast","created":"2022-04-28","cited_by_count":6,"area":null},{"id":"2306.15762","title":"Toward Mesh-Invariant 3D Generative Deep Learning with Geometric Measures","created":"2023-06-27","cited_by_count":6,"area":null},{"id":"2310.15003","title":"Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent Geometries","created":"2023-10-23","cited_by_count":6,"area":null},{"id":"2504.02067","title":"A Truncated Newton Method for Optimal Transport","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2212.03236","title":"Self-Supervised Correspondence Estimation via Multiview Registration","created":"2022-12-06","cited_by_count":5,"area":null},{"id":"2306.04376","title":"Label Shift Quantification with Robustness Guarantees via Distribution Feature Matching","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2110.07202","title":"Unrolled Variational Bayesian Algorithm for Image Blind Deconvolution","created":"2021-10-14","cited_by_count":4,"area":null},{"id":"2206.14148","title":"Memory Safe Computations with XLA Compiler","created":"2022-06-28","cited_by_count":4,"area":null},{"id":"2103.12441","title":"Partial Matching in the Space of Varifolds","created":"2021-03-23","cited_by_count":3,"area":null},{"id":"2109.04757","title":"Low-rank statistical finite elements for scalable model-data synthesis","created":"2021-09-10","cited_by_count":3,"area":null},{"id":"2109.06861","title":"Nonlinearities in Steerable SO(2)-Equivariant CNNs","created":"2021-09-14","cited_by_count":3,"area":null},{"id":"2206.04763","title":"Neural Bregman Divergences for Distance Learning","created":"2022-06-09","cited_by_count":3,"area":null},{"id":"2209.10621","title":"GNPM: Geometric-Aware Neural Parametric Models","created":"2022-09-21","cited_by_count":3,"area":null},{"id":"2311.03087","title":"Persistent Homology for High-dimensional Data Based on Spectral Methods","created":"2023-11-06","cited_by_count":3,"area":null},{"id":"2408.00549","title":"Learning to Embed Distributions via Maximum Kernel Entropy","created":"2024-08-01","cited_by_count":3,"area":null},{"id":"2505.13723","title":"Turbocharging Gaussian Process Inference with Approximate Sketch-and-Project","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2506.12025","title":"Unsupervised Learning for Optimal Transport plan prediction between unbalanced graphs","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2104.14554","title":"MongeNet: Efficient Sampler for Geometric Deep Learning","created":"2021-04-29","cited_by_count":2,"area":null},{"id":"2203.11627","title":"Centered plug-in estimation of Wasserstein distances","created":"2022-03-22","cited_by_count":2,"area":null},{"id":"2209.01498","title":"StreamNet: A WAE for White Matter Streamline Analysis","created":"2022-09-03","cited_by_count":2,"area":null},{"id":"2310.20285","title":"Accelerating Non-Conjugate Gaussian Processes By Trading Off Computation For Uncertainty","created":"2023-10-31","cited_by_count":2,"area":null},{"id":"2312.03311","title":"On the Nystrom Approximation for Preconditioning in Kernel Machines","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2410.08804","title":"Batched Energy-Entropy acquisition for Bayesian Optimization","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2503.02259","title":"HiGP: A high-performance Python package for Gaussian Process","created":"2025-03-04","cited_by_count":2,"area":null},{"id":"2506.10288","title":"ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2111.12139","title":"ChebLieNet: Invariant Spectral Graph NNs Turned Equivariant by Riemannian Geometry on Lie Groups","created":"2021-11-23","cited_by_count":1,"area":null},{"id":"2202.01085","title":"Giga-scale Kernel Matrix Vector Multiplication on GPU","created":"2022-02-02","cited_by_count":1,"area":null},{"id":"2209.15121","title":"Heterogeneous reconstruction of deformable atomic models in Cryo-EM","created":"2022-09-29","cited_by_count":1,"area":null},{"id":"2308.04987","title":"Self-supervised Landmark Learning with Deformation Reconstruction and Cross-subject Consistency Objectives","created":"2023-08-09","cited_by_count":1,"area":null},{"id":"2309.14096","title":"Tracking Control for a Spherical Pendulum via Curriculum Reinforcement Learning","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2310.05019","title":"Compressed online Sinkhorn","created":"2023-10-08","cited_by_count":1,"area":null},{"id":"2404.17344","title":"Fast Evaluation of Additive Kernels: Feature Arrangement, Fourier Methods, and Kernel Derivatives","created":"2024-04-26","cited_by_count":1,"area":null},{"id":"2405.17277","title":"Gradients of Functions of Large Matrices","created":"2024-05-27","cited_by_count":1,"area":null},{"id":"2407.04844","title":"Neural varifolds: an aggregate representation for quantifying the geometry of point clouds","created":"2024-07-05","cited_by_count":1,"area":null},{"id":"2410.21419","title":"High-Dimensional Gaussian Process Regression with Soft Kernel Interpolation","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2503.02606","title":"ARC-Flow : Articulated, Resolution-Agnostic, Correspondence-Free Matching and Interpolation of 3D Shapes Under Flow Fields","created":"2025-03-04","cited_by_count":1,"area":null},{"id":"2503.03156","title":"Dimensionality reduction for homological stability and global structure preservation","created":"2025-03-05","cited_by_count":1,"area":null},{"id":"2602.10378","title":"Flash-SD-KDE: Accelerating SD-KDE with Tensor Cores","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2607.18074","title":"Sobek: Streaming Equivariant Tensor Product Convolutions","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2103.14076","title":"Learning landmark geodesics using Kalman ensembles","created":"2021-03-25","cited_by_count":0,"area":null},{"id":"2111.08498","title":"Reducing the Long Tail Losses in Scientific Emulations with Active Learning","created":"2021-11-15","cited_by_count":0,"area":null},{"id":"2202.13638","title":"GPU-Accelerated Policy Optimization via Batch Automatic Differentiation of Gaussian Processes for Real-World Control","created":"2022-02-28","cited_by_count":0,"area":null},{"id":"2203.09783","title":"ISDE : Independence Structure Density Estimation","created":"2022-03-18","cited_by_count":0,"area":null},{"id":"2204.05665","title":"How to Register a Live onto a Liver ? Partial Matching in the Space of Varifolds","created":"2022-04-12","cited_by_count":0,"area":null},{"id":"2305.17255","title":"FineMorphs: Affine-diffeomorphic sequences for regression","created":"2023-05-26","cited_by_count":0,"area":null},{"id":"2409.15466","title":"Mat\\'ern Kernels for Tunable Implicit Surface Reconstruction","created":"2024-09-23","cited_by_count":0,"area":null},{"id":"2410.06171","title":"Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2501.03383","title":"The Artificial Scientist -- in-transit Machine Learning of Plasma Simulations","created":"2025-01-06","cited_by_count":0,"area":null},{"id":"2506.09357","title":"A new approach for image segmentation based on diffeomorphic registration and gradient fields","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2507.06161","title":"Sinkhorn Normalization of Diffusion Kernels","created":"2025-07-08","cited_by_count":0,"area":null},{"id":"2508.01864","title":"Fast Gaussian process inference by exact Mat\\'ern kernel decomposition","created":"2025-08-03","cited_by_count":0,"area":null},{"id":"2508.08178","title":"3D Human Mesh Estimation from Single View RGBD","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2509.02109","title":"Differentiable Expectation-Maximisation and Applications to Gaussian Mixture Model Optimal Transport","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2512.19743","title":"From Theory to Throughput: CUDA-Optimized APML for Large-Batch 3D Learning","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2604.03815","title":"k-Maximum Inner Product Attention for Graph Transformers and the Expressive Power of GraphGPS","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.27967","title":"Differentiable latent structure discovery for interpretable forecasting in clinical time series","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.00837","title":"Fast Log-Domain Sinkhorn Optimal Transport with Warp-Level GPU Reductions","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2605.17898","title":"Lightweight Gaussian Process Inference in C++ on Metal and CUDA","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.26509","title":"SIKA-GP: Accelerating Gaussian Process Inference with Sparse Inducing Kernel Approximations for Bayesian Deep Learning","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2607.23115","title":"Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2609.04910","title":"Fast Gauss Sums via Flash Attention","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.30379","title":"DanLing NestedTensor: Composable Multi-Ragged Tensors for Deep Learning","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.35349","title":"Quasi Linear Kernel Attention with Infinite Capacity","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38198","title":"FlashDiffusion: Fused Tiled Kernel Spectral Decomposition","created":"2026-09-18","cited_by_count":0,"area":null}],"next_cursor":"100"}