{"total":58,"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":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424,"area":null},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136,"area":null},{"id":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129,"area":null},{"id":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122,"area":null},{"id":"2102.02611","title":"CKConv: Continuous Kernel Convolution For Sequential Data","created":"2021-02-04","cited_by_count":120,"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":"2110.08059","title":"FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes","created":"2021-10-15","cited_by_count":66,"area":null},{"id":"2202.08417","title":"Retrieval-Augmented Reinforcement Learning","created":"2022-02-17","cited_by_count":53,"area":"rag"},{"id":"2309.12252","title":"Parallelizing non-linear sequential models over the sequence length","created":"2023-09-21","cited_by_count":45,"area":null},{"id":"2203.06801","title":"MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks","created":"2022-03-14","cited_by_count":34,"area":null},{"id":"2101.01896","title":"Taxonomy Completion via Triplet Matching Network","created":"2021-01-06","cited_by_count":21,"area":null},{"id":"2305.01638","title":"Sequence Modeling with Multiresolution Convolutional Memory","created":"2023-05-02","cited_by_count":19,"area":null},{"id":"2306.09459","title":"Recurrent Action Transformer with Memory","created":"2023-06-15","cited_by_count":17,"area":"offlinerl"},{"id":"2205.01889","title":"Improving Multi-Document Summarization through Referenced Flexible Extraction with Credit-Awareness","created":"2022-05-04","cited_by_count":13,"area":null},{"id":"2111.08195","title":"MoRe-Fi: Motion-robust and Fine-grained Respiration Monitoring via Deep-Learning UWB Radar","created":"2021-11-16","cited_by_count":11,"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":"2305.11918","title":"PASTS: Progress-Aware Spatio-Temporal Transformer Speaker For Vision-and-Language Navigation","created":"2023-05-19","cited_by_count":8,"area":null},{"id":"2106.03903","title":"PILOT: Introducing Transformers for Probabilistic Sound Event Localization","created":"2021-06-07","cited_by_count":7,"area":null},{"id":"2106.08928","title":"RNNs of RNNs: Recursive Construction of Stable Assemblies of Recurrent Neural Networks","created":"2021-06-16","cited_by_count":7,"area":null},{"id":"2109.09566","title":"Combining Rules and Embeddings via Neuro-Symbolic AI for Knowledge Base Completion","created":"2021-09-16","cited_by_count":7,"area":null},{"id":"2305.16433","title":"Neural Machine Translation for Mathematical Formulae","created":"2023-05-25","cited_by_count":7,"area":null},{"id":"2304.02330","title":"SMPConv: Self-moving Point Representations for Continuous Convolution","created":"2023-04-05","cited_by_count":6,"area":null},{"id":"2409.15022","title":"A Diagonal Structured State Space Model on Loihi 2 for Efficient Streaming Sequence Processing","created":"2024-09-23","cited_by_count":6,"area":"ssm"},{"id":"2103.01521","title":"On the Memory Mechanism of Tensor-Power Recurrent Models","created":"2021-03-02","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":"2406.08128","title":"Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2412.06531","title":"Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation","created":"2024-12-09","cited_by_count":5,"area":"deeprl"},{"id":"2103.01039","title":"Self-Supervised Simultaneous Multi-Step Prediction of Road Dynamics and Cost Map","created":"2021-03-01","cited_by_count":4,"area":null},{"id":"2404.11163","title":"LongVQ: Long Sequence Modeling with Vector Quantization on Structured Memory","created":"2024-04-17","cited_by_count":4,"area":null},{"id":"2501.17086","title":"Accelerated Training through Iterative Gradient Propagation Along the Residual Path","created":"2025-01-28","cited_by_count":4,"area":null},{"id":"2512.15653","title":"Characterizing Mamba's Selective Memory using Auto-Encoders","created":"2025-12-17","cited_by_count":4,"area":"ssm"},{"id":"2106.01001","title":"Warming up recurrent neural networks to maximise reachable multistability greatly improves learning","created":"2021-06-02","cited_by_count":3,"area":null},{"id":"2211.13250","title":"Lempel-Ziv Networks","created":"2022-11-23","cited_by_count":3,"area":null},{"id":"2112.10068","title":"Lerna: Transformer Architectures for Configuring Error Correction Tools for Short- and Long-Read Genome Sequencing","created":"2021-12-19","cited_by_count":2,"area":null},{"id":"2204.08781","title":"LORD: Lower-Dimensional Embedding of Log-Signature in Neural Rough Differential Equations","created":"2022-04-19","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":"2402.17077","title":"Parallelized Spatiotemporal Binding","created":"2024-02-26","cited_by_count":2,"area":null},{"id":"2408.09453","title":"Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling","created":"2024-08-18","cited_by_count":2,"area":null},{"id":"2509.20503","title":"Myosotis: structured computation for attention like layer","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2512.23824","title":"MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling","created":"2025-12-29","cited_by_count":2,"area":null},{"id":"2101.07061","title":"Deep Inertial Odometry with Accurate IMU Preintegration","created":"2021-01-18","cited_by_count":1,"area":null},{"id":"2102.03626","title":"Extremal learning: extremizing the output of a neural network in regression problems","created":"2021-02-06","cited_by_count":1,"area":null},{"id":"2105.14214","title":"Predictive Representation Learning for Language Modeling","created":"2021-05-29","cited_by_count":1,"area":null},{"id":"2106.02516","title":"Improving Computer Generated Dialog with Auxiliary Loss Functions and Custom Evaluation Metrics","created":"2021-06-04","cited_by_count":1,"area":null},{"id":"2305.15385","title":"Behavior quantification as the missing link between fields: Tools for digital psychiatry and their role in the future of neurobiology","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2310.11707","title":"Learning under Label Proportions for Text Classification","created":"2023-10-18","cited_by_count":1,"area":null},{"id":"2401.16299","title":"Enhancing Molecular Property Prediction with Auxiliary Learning and Task-Specific Adaptation","created":"2024-01-29","cited_by_count":1,"area":null},{"id":"2409.00070","title":"Learning to Plan Long-Term for Language Modeling","created":"2024-08-23","cited_by_count":1,"area":null},{"id":"2112.03032","title":"Transfer Learning in Conversational Analysis through Reusing Preprocessing Data as Supervisors","created":"2021-12-02","cited_by_count":0,"area":null},{"id":"2209.11495","title":"Image Classification using Sequence of Pixels","created":"2022-09-23","cited_by_count":0,"area":null},{"id":"2310.01571","title":"Contraction Properties of the Global Workspace Primitive","created":"2023-10-02","cited_by_count":0,"area":null},{"id":"2401.17948","title":"HyperZ$\\cdot$Z$\\cdot$W Operator Connects Slow-Fast Networks for Full Context Interaction","created":"2024-01-31","cited_by_count":0,"area":null},{"id":"2402.15290","title":"Efficient State Space Model via Fast Tensor Convolution and Block Diagonalization","created":"2024-02-23","cited_by_count":0,"area":"ssm"},{"id":"2511.21276","title":"A physics-informed U-Net-LSTM network for nonlinear structural response under seismic excitation","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2603.14077","title":"Enhancing Eye Feature Estimation from Event Data Streams through Adaptive Inference State Space Modeling","created":"2026-03-14","cited_by_count":0,"area":null}],"next_cursor":null}