{"total":86,"rows":[{"id":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408,"area":null},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136,"area":null},{"id":"2101.12249","title":"A Survey of Complex-Valued Neural Networks","created":"2021-01-28","cited_by_count":61,"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":"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":"2103.01649","title":"Learning with Hyperspherical Uniformity","created":"2021-03-02","cited_by_count":35,"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":"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":"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":"2101.05186","title":"MC-LSTM: Mass-Conserving LSTM","created":"2021-01-13","cited_by_count":17,"area":null},{"id":"2106.12901","title":"Recurrent Neural Network from Adder's Perspective: Carry-lookahead RNN","created":"2021-06-22","cited_by_count":16,"area":null},{"id":"2207.00378","title":"Rapid training of quantum recurrent neural networks","created":"2022-07-01","cited_by_count":13,"area":null},{"id":"2507.12142","title":"LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank Adapters","created":"2025-07-16","cited_by_count":13,"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":"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":"2503.05431","title":"Quantum-PEFT: Ultra parameter-efficient fine-tuning","created":"2025-03-07","cited_by_count":11,"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":"2206.06637","title":"RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks","created":"2022-06-14","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":"2410.05499","title":"Unitary convolutions for learning on graphs and groups","created":"2024-10-07","cited_by_count":8,"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":"2112.08950","title":"Stable Long-Term Recurrent Video Super-Resolution","created":"2021-12-16","cited_by_count":6,"area":null},{"id":"2204.10978","title":"All-optical graph representation learning using integrated diffractive photonic computing units","created":"2022-04-23","cited_by_count":6,"area":null},{"id":"2108.00051","title":"Coordinate descent on the orthogonal group for recurrent neural network training","created":"2021-07-30","cited_by_count":5,"area":null},{"id":"2205.08385","title":"Feedback Gradient Descent: Efficient and Stable Optimization with Orthogonality for DNNs","created":"2022-05-12","cited_by_count":5,"area":null},{"id":"2210.01245","title":"Random orthogonal additive filters: a solution to the vanishing/exploding gradient of deep neural networks","created":"2022-10-03","cited_by_count":5,"area":null},{"id":"2212.00228","title":"Gated Recurrent Neural Networks with Weighted Time-Delay Feedback","created":"2022-12-01","cited_by_count":5,"area":null},{"id":"2409.00055","title":"SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models","created":"2024-08-21","cited_by_count":5,"area":null},{"id":"2602.18308","title":"JPmHC Dynamical Isometry via Orthogonal Hyper-Connections","created":"2026-02-20","cited_by_count":5,"area":null},{"id":"2606.06479","title":"Pretraining Recurrent Networks without Recurrence","created":"2026-06-04","cited_by_count":5,"area":null},{"id":"2206.01261","title":"Entangled Residual Mappings","created":"2022-06-02","cited_by_count":4,"area":null},{"id":"2208.06496","title":"Orthogonal Gated Recurrent Unit with Neumann-Cayley Transformation","created":"2022-08-12","cited_by_count":4,"area":null},{"id":"2310.20671","title":"Density Matrix Emulation of Quantum Recurrent Neural Networks for Multivariate Time Series Prediction","created":"2023-10-31","cited_by_count":4,"area":null},{"id":"2604.02309","title":"go-$m$HC: Direct Parameterization of Manifold-Constrained Hyper-Connections via Generalized Orthostochastic Matrices","created":"2026-04-02","cited_by_count":4,"area":null},{"id":"2102.09589","title":"A Differential Geometry Perspective on Orthogonal Recurrent Models","created":"2021-02-18","cited_by_count":3,"area":null},{"id":"2104.10044","title":"BCNN: Binary Complex Neural Network","created":"2021-03-28","cited_by_count":3,"area":null},{"id":"2201.11016","title":"Recency Dropout for Recurrent Recommender Systems","created":"2022-01-26","cited_by_count":3,"area":null},{"id":"2204.04876","title":"Lyapunov-Guided Representation of Recurrent Neural Network Performance","created":"2022-04-11","cited_by_count":3,"area":null},{"id":"2306.09939","title":"Towards Better Orthogonality Regularization with Disentangled Norm in Training Deep CNNs","created":"2023-06-16","cited_by_count":3,"area":null},{"id":"2306.14753","title":"The Deep Arbitrary Polynomial Chaos Neural Network or how Deep Artificial Neural Networks could benefit from Data-Driven Homogeneous Chaos Theory","created":"2023-06-26","cited_by_count":3,"area":null},{"id":"2406.02597","title":"CoNO: Complex Neural Operator for Continous Dynamical Physical Systems","created":"2024-06-01","cited_by_count":3,"area":null},{"id":"2505.08694","title":"A Survey of Deep Learning for Complex Speech Spectrograms","created":"2025-05-13","cited_by_count":3,"area":null},{"id":"2102.11855","title":"Deep Unitary Convolutional Neural Networks","created":"2021-02-23","cited_by_count":2,"area":null},{"id":"2208.05719","title":"Assessing the Unitary RNN as an End-to-End Compositional Model of Syntax","created":"2022-08-11","cited_by_count":2,"area":null},{"id":"2212.05178","title":"State-Regularized Recurrent Neural Networks to Extract Automata and Explain Predictions","created":"2022-12-10","cited_by_count":2,"area":null},{"id":"2302.13812","title":"Adapting Pre-trained Language Models for Quantum Natural Language Processing","created":"2023-02-24","cited_by_count":2,"area":null},{"id":"2408.13211","title":"Optimal Quantum Circuit Design via Unitary Neural Networks","created":"2024-08-23","cited_by_count":2,"area":null},{"id":"2508.12121","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","created":"2025-08-16","cited_by_count":2,"area":null},{"id":"2602.22255","title":"Deep Sequence Modeling with Quantum Dynamics: Language as a Wave Function","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2603.15886","title":"PhasorFlow: A Python Library for Unit Circle Based Computing","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2606.27880","title":"OrthoTryOn: Geometric Orthogonalization for Conflict-Free Unified Fashion Generation","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2106.00003","title":"Parallelized Computation and Backpropagation Under Angle-Parametrized Orthogonal Matrices","created":"2021-05-30","cited_by_count":1,"area":null},{"id":"2207.09350","title":"Riemannian Stochastic Gradient Method for Nested Composition Optimization","created":"2022-07-19","cited_by_count":1,"area":null},{"id":"2401.05967","title":"Block-Diagonal Orthogonal Relation and Matrix Entity for Knowledge Graph Embedding","created":"2024-01-11","cited_by_count":1,"area":null},{"id":"2402.04012","title":"Quantized Approximately Orthogonal Recurrent Neural Networks","created":"2024-02-05","cited_by_count":1,"area":null},{"id":"2406.11882","title":"Applications of Explainable artificial intelligence in Earth system science","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2410.03977","title":"Learning to Balance: Diverse Normalization for Cloth-Changing Person Re-Identification","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2512.17344","title":"Governance-Aware Hybrid Fine-Tuning for Multilingual Large Language Models","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2602.18417","title":"Subgroups of $U(d)$ Induce Natural RNN and Transformer Architectures","created":"2026-02-20","cited_by_count":1,"area":null},{"id":"2605.11855","title":"Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.27673","title":"When do complex-valued neural networks help? A study of representation, geometry, and optimization","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2608.14691","title":"The Quantum Shortcut: Complex Phase-State Dynamics Reduce the Optimization Steps of Sequence Models","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2609.02672","title":"oHC: Orthogonal Hyper-Connections on SO(4) via Quaternions","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2103.07287","title":"Neural Networks with Complex-Valued Weights Have No Spurious Local Minima","created":"2021-01-31","cited_by_count":0,"area":null},{"id":"2106.04088","title":"A Lightweight and Gradient-Stable Neural Layer","created":"2021-06-08","cited_by_count":0,"area":null},{"id":"2109.01731","title":"Acceleration Method for Learning Fine-Layered Optical Neural Networks","created":"2021-09-01","cited_by_count":0,"area":null},{"id":"2112.03467","title":"Spectral Complexity-scaled Generalization Bound of Complex-valued Neural Networks","created":"2021-12-07","cited_by_count":0,"area":null},{"id":"2404.06218","title":"Quantum Circuit $C^*$-algebra Net","created":"2024-04-09","cited_by_count":0,"area":null},{"id":"2407.08214","title":"Towards stable training of parallel continual learning","created":"2024-07-11","cited_by_count":0,"area":null},{"id":"2407.09926","title":"Metric Learning for Clifford Group Equivariant Neural Networks","created":"2024-07-13","cited_by_count":0,"area":null},{"id":"2502.00047","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","created":"2025-01-28","cited_by_count":0,"area":null},{"id":"2505.00929","title":"Compact Recurrent Transformer with Persistent Memory","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2507.18076","title":"Hybrid and Unitary PEFT for Resource-Efficient Large Language Models","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2512.05790","title":"Learnability Window in Gated Recurrent Neural Networks","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2602.15283","title":"Complex-Valued Unitary Representations as Classification Heads for Improved Uncertainty Quantification in Deep Neural Networks","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2603.26188","title":"OSA: Echocardiography Video Segmentation via Orthogonalized State Update and Anatomical Prior-aware Feature Enhancement","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2604.05030","title":"Phase-Associative Memory: Sequence Modeling in Complex Hilbert Space","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2606.15085","title":"An Integrable Token Mixing Layer from the Generalized Yang Baxter Equation","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2606.18324","title":"Why SWAVE May Not Be All You Need:A Concept-Evolution Retrospective on Complex-Valued Recurrent Language Models","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2607.04535","title":"ManifoldFlow: Spectrum-Learnable Stiefel Optimization via SPD Relaxation","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2609.02911","title":"A Spectral Phase Admissibility Certificate for Complex Linear Maps","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2609.19363","title":"Directions That Don't Drift: Stiefel Manifold Routing for Transformer Attention","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.12806","title":"Trainable Quantum-Native Language Models: Dissipative Memory, Capacity Limits, and Hardware Validation","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}