{"list":"other","total":56,"rows":[{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408},{"id":"2406.06484","title":"Parallelizing Linear Transformers with the Delta Rule over Sequence Length","created":"2024-06-10","cited_by_count":396},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"2405.04517","title":"xLSTM: Extended Long Short-Term Memory","created":"2024-05-07","cited_by_count":327},{"id":"2207.02098","title":"Neural Networks and the Chomsky Hierarchy","created":"2022-07-05","cited_by_count":217},{"id":"2402.18668","title":"Simple linear attention language models balance the recall-throughput tradeoff","created":"2024-02-28","cited_by_count":208},{"id":"2404.08819","title":"The Illusion of State in State-Space Models","created":"2024-04-12","cited_by_count":187},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136},{"id":"2411.12537","title":"Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues","created":"2024-11-19","cited_by_count":101},{"id":"2603.15569","title":"Mamba-3: Improved Sequence Modeling using State Space Principles","created":"2026-03-16","cited_by_count":89},{"id":"2502.10297","title":"DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products","created":"2025-02-14","cited_by_count":75},{"id":"2402.09963","title":"Why are Sensitive Functions Hard for Transformers?","created":"2024-02-15","cited_by_count":74},{"id":"2402.19047","title":"Theoretical Foundations of Deep Selective State-Space Models","created":"2024-02-29","cited_by_count":74},{"id":"2102.07850","title":"Differentiable Particle Filtering via Entropy-Regularized Optimal Transport","created":"2021-02-15","cited_by_count":59},{"id":"2106.10800","title":"Lossy Compression for Lossless Prediction","created":"2021-06-21","cited_by_count":52},{"id":"2405.17394","title":"The Expressive Capacity of State Space Models: A Formal Language Perspective","created":"2024-05-27","cited_by_count":46},{"id":"2009.12789","title":"Learning Optimal Representations with the Decodable Information Bottleneck","created":"2020-09-27","cited_by_count":33},{"id":"1902.01224","title":"Estimating the Mixing Time of Ergodic Markov Chains","created":"2019-02-01","cited_by_count":25},{"id":"2010.07452","title":"Near Optimality of Finite Memory Feedback Policies in Partially Observed Markov Decision Processes","created":"2020-10-15","cited_by_count":23},{"id":"2509.22284","title":"Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models","created":"2025-09-26","cited_by_count":16},{"id":"2505.23623","title":"Characterizing the Expressivity of Fixed-Precision Transformer Language Models","created":"2025-05-29","cited_by_count":14},{"id":"1612.02526","title":"Prediction with a Short Memory","created":"2016-12-08","cited_by_count":13},{"id":"2302.14753","title":"Learning Hidden Markov Models Using Conditional Samples","created":"2023-02-28","cited_by_count":12},{"id":"2502.10178","title":"From Markov to Laplace: How Mamba In-Context Learns Markov Chains","created":"2025-02-14","cited_by_count":11},{"id":"2511.21016","title":"Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression","created":"2025-11-26","cited_by_count":11},{"id":"2105.04180","title":"Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning","created":"2021-05-10","cited_by_count":10},{"id":"2406.15131","title":"KalMamba: Towards Efficient Probabilistic State Space Models for RL under Uncertainty","created":"2024-06-21","cited_by_count":9},{"id":"2603.01959","title":"The Expressive Limits of Diagonal SSMs for State-Tracking","created":"2026-03-02","cited_by_count":9},{"id":"2607.07386","title":"Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity","created":"2026-07-08","cited_by_count":9},{"id":"2507.05238","title":"Bridging Expressivity and Scalability with Adaptive Unitary SSMs","created":"2025-07-07","cited_by_count":8},{"id":"2602.10743","title":"Kalman Linear Attention: Parallel Bayesian Filtering For Efficient Language Modelling and State Tracking","created":"2026-02-11","cited_by_count":8},{"id":"2602.14814","title":"Learning State-Tracking from Code Using Linear RNNs","created":"2026-02-16","cited_by_count":6},{"id":"2210.17312","title":"Neural network-based CUSUM for online change-point detection","created":"2022-10-31","cited_by_count":5},{"id":"2211.00335","title":"Recurrent Neural Networks and Universal Approximation of Bayesian Filters","created":"2022-11-01","cited_by_count":5},{"id":"2502.02209","title":"On the Expressivity of Selective State-Space Layers: A Multivariate Polynomial Approach","created":"2025-02-04","cited_by_count":4},{"id":"2506.05065","title":"UnHiPPO: Uncertainty-aware Initialization for State Space Models","created":"2025-06-05","cited_by_count":3},{"id":"1905.10031","title":"Accuracy-Memory Tradeoffs and Phase Transitions in Belief Propagation","created":"2019-05-24","cited_by_count":2},{"id":"2102.00050","title":"Sequential prediction under log-loss and misspecification","created":"2021-01-29","cited_by_count":2},{"id":"2508.10658","title":"Sensitivity of Filter Kernels and Robustness Bounds to Transition and Measurement Kernel Perturbations in Partially Observable Stochastic Control","created":"2025-08-14","cited_by_count":2},{"id":"2509.01254","title":"What Expressivity Theory Misses: Message Passing Complexity for GNNs","created":"2025-09-01","cited_by_count":2},{"id":"2601.13357","title":"On the Relation of State Space Models and Hidden Markov Models","created":"2026-01-19","cited_by_count":2},{"id":"2601.19467","title":"On the Expressiveness of State Space Models via Temporal Logics","created":"2026-01-27","cited_by_count":2},{"id":"2602.17744","title":"Bayesian Optimality of In-Context Learning with Selective State Spaces","created":"2026-02-19","cited_by_count":1},{"id":"2604.02441","title":"Adaptive Learned State Estimation based on KalmanNet","created":"2026-04-02","cited_by_count":1},{"id":"2604.09208","title":"A Predictive View on Streaming Hidden Markov Models","created":"2026-04-10","cited_by_count":1},{"id":"2604.23818","title":"On the Generalization Properties of Selective State-Space Models for Filtering Tasks for Unknown Systems","created":"2026-04-26","cited_by_count":1},{"id":"2605.30100","title":"Chess-World-Model: A 10M-Game Benchmark for Exact State Tracking from Chess Move Sequences","created":"2026-05-28","cited_by_count":1}],"next_cursor":null}