{"total":294,"rows":[{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465,"area":"ssm"},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788,"area":"ssm"},{"id":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608,"area":null},{"id":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408,"area":null},{"id":"2105.12806","title":"A Universal Law of Robustness via Isoperimetry","created":"2021-05-26","cited_by_count":151,"area":null},{"id":"2405.00781","title":"Barren Plateaus in Variational Quantum Computing","created":"2024-05-01","cited_by_count":133,"area":null},{"id":"2102.02611","title":"CKConv: Continuous Kernel Convolution For Sequential Data","created":"2021-02-04","cited_by_count":120,"area":null},{"id":"2401.06104","title":"Transformers are Multi-State RNNs","created":"2024-01-11","cited_by_count":120,"area":"inference"},{"id":"2103.12593","title":"Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks","created":"2021-03-12","cited_by_count":115,"area":null},{"id":"2104.07167","title":"Orthogonalizing Convolutional Layers with the Cayley Transform","created":"2021-04-14","cited_by_count":105,"area":null},{"id":"2311.04823","title":"Hierarchically Gated Recurrent Neural Network for Sequence Modeling","created":"2023-11-08","cited_by_count":102,"area":null},{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84,"area":null},{"id":"2110.07238","title":"On the difficulty of learning chaotic dynamics with RNNs","created":"2021-10-14","cited_by_count":67,"area":null},{"id":"2404.16112","title":"Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challenges","created":"2024-04-24","cited_by_count":64,"area":"ssm"},{"id":"2406.07456","title":"fKAN: Fractional Kolmogorov-Arnold Networks with trainable Jacobi basis functions","created":"2024-06-11","cited_by_count":64,"area":null},{"id":"2101.12249","title":"A Survey of Complex-Valued Neural Networks","created":"2021-01-28","cited_by_count":61,"area":null},{"id":"2306.04406","title":"Generalized Teacher Forcing for Learning Chaotic Dynamics","created":"2023-06-07","cited_by_count":58,"area":null},{"id":"2103.05487","title":"UnICORNN: A recurrent model for learning very long time dependencies","created":"2021-03-09","cited_by_count":56,"area":null},{"id":"2410.19538","title":"Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series","created":"2024-10-25","cited_by_count":43,"area":"diffusion"},{"id":"2502.10818","title":"On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning","created":"2025-02-15","cited_by_count":43,"area":null},{"id":"2110.04840","title":"Heavy Ball Neural Ordinary Differential Equations","created":"2021-10-10","cited_by_count":42,"area":null},{"id":"2110.04744","title":"Long Expressive Memory for Sequence Modeling","created":"2021-10-10","cited_by_count":41,"area":null},{"id":"2406.01775","title":"OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models","created":"2024-06-03","cited_by_count":39,"area":null},{"id":"2410.03943","title":"Oscillatory State-Space Models","created":"2024-10-04","cited_by_count":39,"area":null},{"id":"2410.01201","title":"Were RNNs All We Needed?","created":"2024-10-02","cited_by_count":38,"area":null},{"id":"2102.07432","title":"Fast and accurate optimization on the orthogonal manifold without retraction","created":"2021-02-15","cited_by_count":35,"area":null},{"id":"2103.01649","title":"Learning with Hyperspherical Uniformity","created":"2021-03-02","cited_by_count":35,"area":null},{"id":"2203.06345","title":"The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy","created":"2022-03-12","cited_by_count":35,"area":null},{"id":"2102.07091","title":"Decentralized Riemannian Gradient Descent on the Stiefel Manifold","created":"2021-02-14","cited_by_count":33,"area":null},{"id":"2104.05097","title":"Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networks","created":"2021-04-11","cited_by_count":30,"area":null},{"id":"2209.02681","title":"How important are activation functions in regression and classification? A survey, performance comparison, and future directions","created":"2022-09-06","cited_by_count":29,"area":null},{"id":"2211.11176","title":"Modeling Multivariate Biosignals With Graph Neural Networks and Structured State Space Models","created":"2022-11-21","cited_by_count":29,"area":"ssm"},{"id":"2307.05432","title":"Self-Supervised Learning with Lie Symmetries for Partial Differential Equations","created":"2023-07-11","cited_by_count":29,"area":null},{"id":"2205.14550","title":"Machine Learning for Microcontroller-Class Hardware: A Review","created":"2022-05-29","cited_by_count":28,"area":null},{"id":"2203.05483","title":"projUNN: efficient method for training deep networks with unitary matrices","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2403.06213","title":"$V_kD:$ Improving Knowledge Distillation using Orthogonal Projections","created":"2024-03-10","cited_by_count":26,"area":"distill"},{"id":"2405.21064","title":"Recurrent neural networks: vanishing and exploding gradients are not the end of the story","created":"2024-05-31","cited_by_count":25,"area":null},{"id":"2303.16940","title":"T-FFTRadNet: Object Detection with Swin Vision Transformers from Raw ADC Radar Signals","created":"2023-03-29","cited_by_count":24,"area":null},{"id":"2302.08210","title":"A Survey of Geometric Optimization for Deep Learning: From Euclidean Space to Riemannian Manifold","created":"2023-02-16","cited_by_count":21,"area":null},{"id":"2312.06837","title":"Spectral State Space Models","created":"2023-12-11","cited_by_count":21,"area":null},{"id":"2408.11778","title":"Sum of Squares Circuits","created":"2024-08-21","cited_by_count":21,"area":null},{"id":"2105.04854","title":"Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity","created":"2021-05-11","cited_by_count":20,"area":null},{"id":"2112.03328","title":"Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognition","created":"2021-12-06","cited_by_count":20,"area":null},{"id":"2507.13338","title":"Training Transformers with Enforced Lipschitz Constants","created":"2025-07-17","cited_by_count":20,"area":null},{"id":"2105.13205","title":"Hamiltonian Deep Neural Networks Guaranteeing Non-vanishing Gradients by Design","created":"2021-05-27","cited_by_count":18,"area":null},{"id":"2111.03976","title":"CubeLearn: End-to-end Learning for Human Motion Recognition from Raw mmWave Radar Signals","created":"2021-11-07","cited_by_count":18,"area":null},{"id":"2303.16510","title":"Infeasible Deterministic, Stochastic, and Variance-Reduction Algorithms for Optimization under Orthogonality Constraints","created":"2023-03-29","cited_by_count":18,"area":null},{"id":"2310.01698","title":"Robustifying State-space Models for Long Sequences via Approximate Diagonalization","created":"2023-10-02","cited_by_count":18,"area":null},{"id":"2405.06147","title":"State-Free Inference of State-Space Models: The Transfer Function Approach","created":"2024-05-10","cited_by_count":18,"area":null},{"id":"2101.05186","title":"MC-LSTM: Mass-Conserving LSTM","created":"2021-01-13","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":"2108.05623","title":"Existence, Stability and Scalability of Orthogonal Convolutional Neural Networks","created":"2021-08-12","cited_by_count":16,"area":null},{"id":"2309.08045","title":"Traveling Waves Encode the Recent Past and Enhance Sequence Learning","created":"2023-09-03","cited_by_count":16,"area":null},{"id":"2405.20799","title":"Rough Transformers: Lightweight and Continuous Time Series Modelling through Signature Patching","created":"2024-05-31","cited_by_count":16,"area":null},{"id":"2103.00673","title":"Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training","created":"2021-03-01","cited_by_count":15,"area":null},{"id":"2306.09739","title":"Stabilized Neural Differential Equations for Learning Dynamics with Explicit Constraints","created":"2023-06-16","cited_by_count":15,"area":null},{"id":"2403.12335","title":"Temporally Consistent Koopman Autoencoders for Forecasting Dynamical Systems","created":"2024-03-19","cited_by_count":15,"area":null},{"id":"2210.01407","title":"Homotopy-based training of NeuralODEs for accurate dynamics discovery","created":"2022-10-04","cited_by_count":14,"area":null},{"id":"2303.09261","title":"Orthogonal Directions Constrained Gradient Method: from non-linear equality constraints to Stiefel manifold","created":"2023-03-16","cited_by_count":14,"area":null},{"id":"2306.12965","title":"Improved Financial Forecasting via Quantum Machine Learning","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2207.00378","title":"Rapid training of quantum recurrent neural networks","created":"2022-07-01","cited_by_count":13,"area":null},{"id":"2306.01485","title":"Robust low-rank training via approximate orthonormal constraints","created":"2023-06-02","cited_by_count":13,"area":null},{"id":"2102.07824","title":"An Operator Theoretic Approach for Analyzing Sequence Neural Networks","created":"2021-02-15","cited_by_count":12,"area":null},{"id":"2112.09046","title":"Distributed neural network control with dependability guarantees: a compositional port-Hamiltonian approach","created":"2021-12-16","cited_by_count":12,"area":null},{"id":"2210.08959","title":"Flipped Classroom: Effective Teaching for Time Series Forecasting","created":"2022-10-17","cited_by_count":12,"area":null},{"id":"2404.12794","title":"MambaMOS: LiDAR-based 3D Moving Object Segmentation with Motion-aware State Space Model","created":"2024-04-19","cited_by_count":12,"area":null},{"id":"2601.23000","title":"Mano: Restriking Manifold Optimization for LLM Training","created":"2026-01-30","cited_by_count":12,"area":null},{"id":"2101.07833","title":"Implicit Bias of Linear RNNs","created":"2021-01-19","cited_by_count":11,"area":null},{"id":"2107.09055","title":"Stock price prediction using BERT and GAN","created":"2021-07-18","cited_by_count":11,"area":null},{"id":"2112.14949","title":"Decentralized Optimization Over the Stiefel Manifold by an Approximate Augmented Lagrangian Function","created":"2021-12-30","cited_by_count":11,"area":null},{"id":"2205.14173","title":"Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport","created":"2022-05-27","cited_by_count":11,"area":null},{"id":"2207.13649","title":"Explain My Surprise: Learning Efficient Long-Term Memory by Predicting Uncertain Outcomes","created":"2022-07-27","cited_by_count":11,"area":null},{"id":"2302.08286","title":"Theory and Implementation of Complex-Valued Neural Networks","created":"2023-02-16","cited_by_count":11,"area":null},{"id":"2406.10019","title":"Group and Shuffle: Efficient Structured Orthogonal Parametrization","created":"2024-06-14","cited_by_count":11,"area":null},{"id":"2503.05431","title":"Quantum-PEFT: Ultra parameter-efficient fine-tuning","created":"2025-03-07","cited_by_count":11,"area":null},{"id":"2109.00020","title":"Working Memory Connections for LSTM","created":"2021-08-31","cited_by_count":10,"area":null},{"id":"2110.07034","title":"How Does Momentum Benefit Deep Neural Networks Architecture Design? A Few Case Studies","created":"2021-10-13","cited_by_count":10,"area":null},{"id":"2201.12133","title":"O-ViT: Orthogonal Vision Transformer","created":"2022-01-28","cited_by_count":10,"area":null},{"id":"2304.11461","title":"Recurrent Neural Networks and Long Short-Term Memory Networks: Tutorial and Survey","created":"2023-04-22","cited_by_count":10,"area":null},{"id":"2306.11941","title":"Efficient Dynamics Modeling in Interactive Environments with Koopman Theory","created":"2023-06-20","cited_by_count":10,"area":null},{"id":"2312.16045","title":"Algebraic Positional Encodings","created":"2023-12-26","cited_by_count":10,"area":null},{"id":"2508.17901","title":"Riemannian Optimization for LoRA on the Stiefel Manifold","created":"2025-08-25","cited_by_count":10,"area":null},{"id":"2308.08989","title":"Neural oscillators for generalization of physics-informed machine learning","created":"2023-08-17","cited_by_count":9,"area":null},{"id":"2601.00417","title":"Deep Delta Learning","created":"2026-01-01","cited_by_count":9,"area":null},{"id":"2101.09346","title":"On the Local Linear Rate of Consensus on the Stiefel Manifold","created":"2021-01-22","cited_by_count":8,"area":null},{"id":"2204.00740","title":"Path Development Network with Finite-dimensional Lie Group Representation","created":"2022-04-02","cited_by_count":8,"area":null},{"id":"2310.02012","title":"Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion","created":"2023-10-03","cited_by_count":8,"area":null},{"id":"2405.17283","title":"Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery","created":"2024-05-27","cited_by_count":8,"area":null},{"id":"2410.05499","title":"Unitary convolutions for learning on graphs and groups","created":"2024-10-07","cited_by_count":8,"area":null},{"id":"2505.09022","title":"Block-Biased Mamba for Long-Range Sequence Processing","created":"2025-05-13","cited_by_count":8,"area":"ssm"},{"id":"2103.16584","title":"Parameterized Hypercomplex Graph Neural Networks for Graph Classification","created":"2021-03-30","cited_by_count":7,"area":null},{"id":"2105.05944","title":"Slower is Better: Revisiting the Forgetting Mechanism in LSTM for Slower Information Decay","created":"2021-05-12","cited_by_count":7,"area":null},{"id":"2106.09121","title":"Scaling-up Diverse Orthogonal Convolutional Networks with a Paraunitary Framework","created":"2021-06-16","cited_by_count":7,"area":null},{"id":"2210.00973","title":"NCVX: A General-Purpose Optimization Solver for Constrained Machine and Deep Learning","created":"2022-10-03","cited_by_count":7,"area":null},{"id":"2409.10489","title":"Flash STU: Fast Spectral Transform Units","created":"2024-09-16","cited_by_count":7,"area":null},{"id":"2112.08950","title":"Stable Long-Term Recurrent Video Super-Resolution","created":"2021-12-16","cited_by_count":6,"area":null},{"id":"2203.00546","title":"Optimal quantum dataset for learning a unitary transformation","created":"2022-03-01","cited_by_count":6,"area":null},{"id":"2308.12585","title":"Persistent learning signals and working memory without continuous attractors","created":"2023-08-24","cited_by_count":6,"area":null},{"id":"2405.08967","title":"Gradient-Free Training of Recurrent Neural Networks using Random Perturbations","created":"2024-05-14","cited_by_count":6,"area":null},{"id":"2405.20980","title":"Neural Gaussian Scale-Space Fields","created":"2024-05-31","cited_by_count":6,"area":null}],"next_cursor":"100"}