{"total":143,"rows":[{"id":"2407.06023","title":"Distilling System 2 into System 1","created":"2024-07-08","cited_by_count":159,"area":"lr"},{"id":"2403.14404","title":"Physics-Informed Diffusion Models","created":"2024-03-21","cited_by_count":90,"area":"diffusion"},{"id":"2110.09813","title":"Multi-Objective Loss Balancing for Physics-Informed Deep Learning","created":"2021-10-19","cited_by_count":87,"area":null},{"id":"2310.00120","title":"Multi-Grid Tensorized Fourier Neural Operator for High-Resolution PDEs","created":"2023-09-29","cited_by_count":68,"area":null},{"id":"2206.10745","title":"Derivative-Informed Neural Operator: An Efficient Framework for High-Dimensional Parametric Derivative Learning","created":"2022-06-21","cited_by_count":44,"area":null},{"id":"2107.00940","title":"Inverse-Dirichlet Weighting Enables Reliable Training of Physics Informed Neural Networks","created":"2021-07-02","cited_by_count":43,"area":null},{"id":"2106.06898","title":"Learning Dissipative Dynamics in Chaotic Systems","created":"2021-06-13","cited_by_count":42,"area":null},{"id":"2405.03658","title":"A review on data-driven constitutive laws for solids","created":"2024-05-06","cited_by_count":35,"area":null},{"id":"2305.08466","title":"Nearly Optimal VC-Dimension and Pseudo-Dimension Bounds for Deep Neural Network Derivatives","created":"2023-05-15","cited_by_count":30,"area":null},{"id":"2110.14149","title":"Diversity Matters When Learning From Ensembles","created":"2021-10-27","cited_by_count":27,"area":null},{"id":"2205.14812","title":"TaSIL: Taylor Series Imitation Learning","created":"2022-05-30","cited_by_count":21,"area":"offlinerl"},{"id":"2402.19242","title":"Derivative-enhanced Deep Operator Network","created":"2024-02-29","cited_by_count":19,"area":null},{"id":"2111.12187","title":"Input Convex Gradient Networks","created":"2021-11-23","cited_by_count":17,"area":null},{"id":"2410.02035","title":"Tuning Frequency Bias of State Space Models","created":"2024-10-02","cited_by_count":17,"area":null},{"id":"2301.12923","title":"On student-teacher deviations in distillation: does it pay to disobey?","created":"2023-01-30","cited_by_count":16,"area":"distill"},{"id":"2204.12088","title":"A physics-informed deep neural network for surrogate modeling in classical elasto-plasticity","created":"2022-04-26","cited_by_count":15,"area":null},{"id":"2103.01007","title":"Error Estimates for the Deep Ritz Method with Boundary Penalty","created":"2021-03-01","cited_by_count":14,"area":null},{"id":"2106.03441","title":"Attention Temperature Matters in Abstractive Summarization Distillation","created":"2021-06-07","cited_by_count":14,"area":null},{"id":"2402.00152","title":"Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss","created":"2024-01-31","cited_by_count":14,"area":null},{"id":"2505.08740","title":"Sensitivity-Constrained Fourier Neural Operators for Forward and Inverse Problems in Parametric Differential Equations","created":"2025-05-13","cited_by_count":14,"area":null},{"id":"2109.14960","title":"Prune Your Model Before Distill It","created":"2021-09-30","cited_by_count":12,"area":"distill"},{"id":"2205.01915","title":"Generalized Knowledge Distillation via Relationship Matching","created":"2022-05-04","cited_by_count":12,"area":"distill"},{"id":"2211.06625","title":"CACTO: Continuous Actor-Critic with Trajectory Optimization -- Towards global optimality","created":"2022-11-12","cited_by_count":12,"area":null},{"id":"2201.08363","title":"Physics-informed neural networks for modeling rate- and temperature-dependent plasticity","created":"2022-01-20","cited_by_count":11,"area":null},{"id":"2205.07331","title":"Sobolev Acceleration and Statistical Optimality for Learning Elliptic Equations via Gradient Descent","created":"2022-05-15","cited_by_count":11,"area":null},{"id":"2306.00945","title":"CS4ML: A general framework for active learning with arbitrary data based on Christoffel functions","created":"2023-06-01","cited_by_count":11,"area":null},{"id":"2502.00472","title":"Binned Spectral Power Loss for Improved Prediction of Chaotic Systems","created":"2025-02-01","cited_by_count":10,"area":null},{"id":"2303.14496","title":"Learning with Explanation Constraints","created":"2023-03-25","cited_by_count":8,"area":null},{"id":"2509.05117","title":"HyPINO: Multi-Physics Neural Operators via HyperPINNs and the Method of Manufactured Solutions","created":"2025-09-05","cited_by_count":8,"area":null},{"id":"2112.00725","title":"The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image","created":"2021-12-01","cited_by_count":7,"area":null},{"id":"2301.13338","title":"Continuous Spatiotemporal Transformers","created":"2023-01-31","cited_by_count":7,"area":null},{"id":"2304.01636","title":"Label-guided Attention Distillation for Lane Segmentation","created":"2023-04-04","cited_by_count":7,"area":null},{"id":"2308.14789","title":"Scattering with Neural Operators","created":"2023-08-28","cited_by_count":7,"area":null},{"id":"2408.13237","title":"JacNet: Learning Functions with Structured Jacobians","created":"2024-08-23","cited_by_count":7,"area":null},{"id":"2207.10395","title":"Sobolev Training for Implicit Neural Representations with Approximated Image Derivatives","created":"2022-07-21","cited_by_count":6,"area":null},{"id":"2312.03286","title":"Indirect Gradient Matching for Adversarial Robust Distillation","created":"2023-12-06","cited_by_count":6,"area":null},{"id":"2409.02342","title":"Optimal sampling for least-squares approximation","created":"2024-09-04","cited_by_count":6,"area":null},{"id":"2102.01963","title":"Local Critic Training for Model-Parallel Learning of Deep Neural Networks","created":"2021-02-03","cited_by_count":5,"area":null},{"id":"2103.06972","title":"Federated Functional Gradient Boosting","created":"2021-03-11","cited_by_count":5,"area":null},{"id":"2209.09006","title":"Enforcing the consensus between Trajectory Optimization and Policy Learning for precise robot control","created":"2022-09-19","cited_by_count":5,"area":null},{"id":"2401.06820","title":"QCQP-Net: Reliably Learning Feasible Alternating Current Optimal Power Flow Solutions Under Constraints","created":"2024-01-11","cited_by_count":5,"area":null},{"id":"2402.09084","title":"Sobolev Training for Operator Learning","created":"2024-02-14","cited_by_count":5,"area":null},{"id":"2603.00618","title":"Multi-Domain Riemannian Graph Gluing for Building Graph Foundation Models","created":"2026-02-28","cited_by_count":5,"area":null},{"id":"2309.15244","title":"Homotopy Relaxation Training Algorithms for Infinite-Width Two-Layer ReLU Neural Networks","created":"2023-09-26","cited_by_count":4,"area":null},{"id":"2311.04779","title":"Optimal Deep Neural Network Approximation for Korobov Functions with respect to Sobolev Norms","created":"2023-11-08","cited_by_count":4,"area":null},{"id":"2312.10666","title":"CACTO-SL: Using Sobolev Learning to improve Continuous Actor-Critic with Trajectory Optimization","created":"2023-12-17","cited_by_count":4,"area":null},{"id":"2608.01263","title":"Distill What the Student Can See: Fisher-Projected On-Policy Distillation for Vision-Language Models","created":"2026-08-02","cited_by_count":4,"area":"mllm"},{"id":"2102.04208","title":"Contrastive Embeddings for Neural Architectures","created":"2021-02-08","cited_by_count":3,"area":null},{"id":"2209.06905","title":"Graph Neural Network Based Node Deployment for Throughput Enhancement","created":"2022-08-19","cited_by_count":3,"area":null},{"id":"2404.00050","title":"Grappa -- A Machine Learned Molecular Mechanics Force Field","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2503.01178","title":"Differentiable Information Enhanced Model-Based Reinforcement Learning","created":"2025-03-03","cited_by_count":3,"area":"deeprl"},{"id":"2504.07976","title":"EquiNO: A Physics-Informed Neural Operator for Multiscale Simulations","created":"2025-03-27","cited_by_count":3,"area":null},{"id":"2509.19773","title":"Sobolev acceleration for neural networks","created":"2025-09-24","cited_by_count":3,"area":null},{"id":"2512.23643","title":"Simultaneous Approximation of the Score Function and Its Derivatives by Deep Neural Networks","created":"2025-12-29","cited_by_count":3,"area":null},{"id":"2603.20410","title":"SLE-FNO: Single-Layer Extensions for Task-Agnostic Continual Learning in Fourier Neural Operators","created":"2026-03-20","cited_by_count":3,"area":null},{"id":"2111.08626","title":"Adjoint-Matching Neural Network Surrogates for Fast 4D-Var Data Assimilation","created":"2021-11-16","cited_by_count":2,"area":null},{"id":"2404.17365","title":"Similarity Equivariant Graph Neural Networks for Homogenization of Metamaterials","created":"2024-04-26","cited_by_count":2,"area":null},{"id":"2407.16466","title":"Sobolev neural network with residual weighting as a surrogate in linear and non-linear mechanics","created":"2024-07-23","cited_by_count":2,"area":null},{"id":"2410.02132","title":"Nonuniform random feature models using derivative information","created":"2024-10-03","cited_by_count":2,"area":null},{"id":"2505.11342","title":"Sobolev Training of End-to-End Optimization Proxies","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2512.06417","title":"Hankel-FNO: Fast Underwater Acoustic Charting Via Physics-Encoded Fourier Neural Operator","created":"2025-12-06","cited_by_count":2,"area":null},{"id":"2603.07705","title":"Deep Incentive Design with Differentiable Equilibrium Blocks","created":"2026-03-08","cited_by_count":2,"area":null},{"id":"2603.10777","title":"Dynamics-Informed Deep Learning for Predicting Extreme Events","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2604.09543","title":"ANTIC: Adaptive Neural Temporal In-situ Compressor","created":"2026-04-10","cited_by_count":2,"area":null},{"id":"2605.14939","title":"Real-time virtual circuits for plasma shape control via neural network emulators","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2112.02077","title":"MD-inferred neural network monoclinic finite-strain hyperelasticity models for $\\beta$-HMX: Sobolev training and validation against physical constraints","created":"2021-11-29","cited_by_count":1,"area":null},{"id":"2205.05383","title":"Automated differential equation solver based on the parametric approximation optimization","created":"2022-05-11","cited_by_count":1,"area":null},{"id":"2209.07080","title":"Layerwise Bregman Representation Learning with Applications to Knowledge Distillation","created":"2022-09-15","cited_by_count":1,"area":"distill"},{"id":"2301.13514","title":"Fourier Sensitivity and Regularization of Computer Vision Models","created":"2023-01-31","cited_by_count":1,"area":null},{"id":"2305.13236","title":"ADA-GP: Accelerating DNN Training By Adaptive Gradient Prediction","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2307.13517","title":"Towards Long-Term predictions of Turbulence using Neural Operators","created":"2023-07-25","cited_by_count":1,"area":null},{"id":"2401.14336","title":"Progressive Multi-task Anti-Noise Learning and Distilling Frameworks for Fine-grained Vehicle Recognition","created":"2024-01-25","cited_by_count":1,"area":null},{"id":"2404.00758","title":"From Robustness to Improved Generalization and Calibration in Pre-trained Language Models","created":"2024-03-31","cited_by_count":1,"area":null},{"id":"2407.04871","title":"Improving Knowledge Distillation in Transfer Learning with Layer-wise Learning Rates","created":"2024-07-05","cited_by_count":1,"area":"distill"},{"id":"2407.12598","title":"Estimate Epidemiological Parameters given Partial Observations based on Algebraically Observable PINNs","created":"2024-07-17","cited_by_count":1,"area":null},{"id":"2505.09851","title":"ZENN: A Thermodynamics-Inspired Computational Framework for Heterogeneous Data-Driven Modeling","created":"2025-05-14","cited_by_count":1,"area":null},{"id":"2506.13120","title":"Accelerating PDE-Constrained Optimization by the Derivative of Neural Operators","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2508.03411","title":"SlotMatch: Distilling Object-Centric Representations for Unsupervised Video Segmentation","created":"2025-08-05","cited_by_count":1,"area":"distill"},{"id":"2509.14219","title":"Data Denoising and Derivative Estimation for Data-Driven Modeling of Nonlinear Dynamical Systems","created":"2025-09-17","cited_by_count":1,"area":null},{"id":"2509.24411","title":"Hybrid Layer-Wise ANN-SNN With Surrogate Spike Encoding-Decoding Structure","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2512.07162","title":"DeepSVM: Learning Stochastic Volatility Models with Physics-Informed Deep Operator Networks","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2604.19011","title":"Accelerating trajectory optimization with Sobolev-trained diffusion policies","created":"2026-04-21","cited_by_count":1,"area":"diffusion"},{"id":"2605.15463","title":"Layer-wise Derivative Controlled Networks","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2609.33347","title":"MultiEcho: An Experimental Science of Learned Worlds","created":"2026-09-27","cited_by_count":1,"area":"wm"},{"id":"2105.01957","title":"Perceptual Gradient Networks","created":"2021-05-05","cited_by_count":0,"area":null},{"id":"2205.13933","title":"Standalone Neural ODEs with Sensitivity Analysis","created":"2022-05-27","cited_by_count":0,"area":null},{"id":"2206.03304","title":"On the balance between the training time and interpretability of neural ODE for time series modelling","created":"2022-06-07","cited_by_count":0,"area":null},{"id":"2301.00181","title":"Smooth Mathematical Function from Compact Neural Networks","created":"2022-12-31","cited_by_count":0,"area":null},{"id":"2302.14182","title":"Taylor TD-learning","created":"2023-02-27","cited_by_count":0,"area":null},{"id":"2306.04919","title":"A Deep Probabilistic Flow-Based Framework for Unsupervised Cross-Domain Soft Sensing","created":"2023-06-08","cited_by_count":0,"area":null},{"id":"2309.16391","title":"2-Cats: 2D Copula Approximating Transforms","created":"2023-09-28","cited_by_count":0,"area":null},{"id":"2310.00946","title":"Distilling Influences to Mitigate Prediction Churn in Graph Neural Networks","created":"2023-10-02","cited_by_count":0,"area":"distill"},{"id":"2310.02806","title":"MP-FVM: Enhancing Finite Volume Method for Water Infiltration Modeling in Unsaturated Soils via Message-passing Encoder-decoder Network","created":"2023-10-04","cited_by_count":0,"area":null},{"id":"2312.03510","title":"Towards Sobolev Pruning","created":"2023-12-06","cited_by_count":0,"area":null},{"id":"2312.13223","title":"StableKD: Breaking Inter-block Optimization Entanglement for Stable Knowledge Distillation","created":"2023-12-20","cited_by_count":0,"area":"distill"},{"id":"2402.17232","title":"Two-scale Neural Networks for Partial Differential Equations with Small Parameters","created":"2024-02-27","cited_by_count":0,"area":null},{"id":"2404.07361","title":"Gradient Networks","created":"2024-04-10","cited_by_count":0,"area":null},{"id":"2408.16138","title":"Thinner Latent Spaces: Detecting Dimension and Imposing Invariance with Conformal Autoencoders","created":"2024-08-28","cited_by_count":0,"area":null},{"id":"2409.01914","title":"GradINN: Gradient Informed Neural Network","created":"2024-09-03","cited_by_count":0,"area":null},{"id":"2412.16886","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","created":"2024-12-22","cited_by_count":0,"area":null}],"next_cursor":"100"}