{"total":105,"rows":[{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401,"area":"moe"},{"id":"2406.06484","title":"Parallelizing Linear Transformers with the Delta Rule over Sequence Length","created":"2024-06-10","cited_by_count":396,"area":null},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2406.07887","title":"An Empirical Study of Mamba-based Language Models","created":"2024-06-12","cited_by_count":186,"area":"ssm"},{"id":"2406.07522","title":"Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling","created":"2024-06-11","cited_by_count":174,"area":"ssm"},{"id":"2405.16712","title":"Zamba: A Compact 7B SSM Hybrid Model","created":"2024-05-26","cited_by_count":124,"area":null},{"id":"2409.02889","title":"LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture","created":"2024-09-04","cited_by_count":102,"area":"mllm"},{"id":"2411.13676","title":"Hymba: A Hybrid-head Architecture for Small Language Models","created":"2024-11-20","cited_by_count":99,"area":null},{"id":"2403.01590","title":"The Hidden Attention of Mamba Models","created":"2024-03-03","cited_by_count":91,"area":"ssm"},{"id":"2512.24695","title":"Nested Learning: The Illusion of Deep Learning Architectures","created":"2025-12-31","cited_by_count":72,"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":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59,"area":null},{"id":"2404.18861","title":"Visual Mamba: A Survey and New Outlooks","created":"2024-04-29","cited_by_count":41,"area":"ssm"},{"id":"2408.01129","title":"A Survey of Mamba","created":"2024-08-02","cited_by_count":39,"area":"ssm"},{"id":"2507.06457","title":"A Systematic Analysis of Hybrid Linear Attention","created":"2025-07-08","cited_by_count":39,"area":null},{"id":"2411.19379","title":"Marconi: Prefix Caching for the Era of Hybrid LLMs","created":"2024-11-28","cited_by_count":31,"area":null},{"id":"2511.05963","title":"Next-Latent Prediction Transformers Learn Compact World Models","created":"2025-11-08","cited_by_count":31,"area":"wm"},{"id":"2405.15463","title":"PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysis","created":"2024-05-24","cited_by_count":26,"area":"ssm"},{"id":"2406.01159","title":"Dimba: Transformer-Mamba Diffusion Models","created":"2024-06-03","cited_by_count":26,"area":"diffusion"},{"id":"2407.10005","title":"Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond","created":"2024-07-13","cited_by_count":24,"area":null},{"id":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2405.15214","title":"PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning","created":"2024-05-24","cited_by_count":21,"area":null},{"id":"2411.15242","title":"The Zamba2 Suite: Technical Report","created":"2024-11-22","cited_by_count":21,"area":null},{"id":"2501.00658","title":"Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing","created":"2024-12-31","cited_by_count":18,"area":"ssm"},{"id":"2408.06966","title":"DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs","created":"2024-08-13","cited_by_count":17,"area":"ssm"},{"id":"2410.09385","title":"Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models","created":"2024-10-12","cited_by_count":17,"area":null},{"id":"2406.07138","title":"An Efficient Recipe for Long Context Extension via Middle-Focused Positional Encoding","created":"2024-06-11","cited_by_count":16,"area":null},{"id":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2509.19633","title":"Mamba Modulation: On the Length Generalization of Mamba","created":"2025-09-23","cited_by_count":16,"area":"ssm"},{"id":"2504.18574","title":"Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism","created":"2025-04-22","cited_by_count":15,"area":null},{"id":"2511.18890","title":"Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models","created":"2025-11-24","cited_by_count":15,"area":null},{"id":"2406.08973","title":"XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning","created":"2024-06-13","cited_by_count":14,"area":"deeprl"},{"id":"2410.02167","title":"Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis","created":"2024-10-03","cited_by_count":14,"area":"lr"},{"id":"2410.05603","title":"Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition","created":"2024-10-08","cited_by_count":14,"area":"mechinterp"},{"id":"2505.00315","title":"Mixture of Sparse Attention: Content-Based Learnable Sparse Attention via Expert-Choice Routing","created":"2025-05-01","cited_by_count":14,"area":"moe"},{"id":"2510.04800","title":"Hybrid Architectures for Language Models: Systematic Analysis and Design Insights","created":"2025-10-06","cited_by_count":14,"area":"ssm"},{"id":"2405.15618","title":"MLPs Learn In-Context on Regression and Classification Tasks","created":"2024-05-24","cited_by_count":13,"area":null},{"id":"2408.15496","title":"ReMamba: Equip Mamba with Effective Long-Sequence Modeling","created":"2024-08-28","cited_by_count":13,"area":"ssm"},{"id":"2504.04308","title":"Gating is Weighting: Understanding Gated Linear Attention through In-context Learning","created":"2025-04-06","cited_by_count":12,"area":null},{"id":"2410.01288","title":"Mitigating Copy Bias in In-Context Learning through Neuron Pruning","created":"2024-10-02","cited_by_count":11,"area":null},{"id":"2410.09016","title":"Parameter-Efficient Fine-Tuning of State Space Models","created":"2024-10-11","cited_by_count":11,"area":"ssm"},{"id":"2411.04168","title":"DiMSUM: Diffusion Mamba -- A Scalable and Unified Spatial-Frequency Method for Image Generation","created":"2024-11-06","cited_by_count":11,"area":"diffusion"},{"id":"2502.10178","title":"From Markov to Laplace: How Mamba In-Context Learns Markov Chains","created":"2025-02-14","cited_by_count":11,"area":"ssm"},{"id":"2509.10345","title":"Towards Understanding Visual Grounding in Visual Language Models","created":"2025-09-12","cited_by_count":10,"area":"mllm"},{"id":"2407.08112","title":"How Well Can a Long Sequence Model Model Long Sequences? Comparing Architechtural Inductive Biases on Long-Context Abilities","created":"2024-07-11","cited_by_count":9,"area":null},{"id":"2410.01485","title":"A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts","created":"2024-10-02","cited_by_count":9,"area":"inference"},{"id":"2409.08530","title":"Integration of Mamba and Transformer -- MAT for Long-Short Range Time Series Forecasting with Application to Weather Dynamics","created":"2024-09-13","cited_by_count":7,"area":"ssm"},{"id":"2410.07145","title":"Stuffed Mamba: Oversized States Lead to the Inability to Forget","created":"2024-10-09","cited_by_count":7,"area":"ssm"},{"id":"2407.05591","title":"On the Power of Convolution Augmented Transformer","created":"2024-07-08","cited_by_count":6,"area":null},{"id":"2409.05395","title":"Shaking Up VLMs: Comparing Transformers and Structured State Space Models for Vision & Language Modeling","created":"2024-09-09","cited_by_count":6,"area":"mllm"},{"id":"2602.11374","title":"Retrieval-Aware Distillation for Transformer-SSM Hybrids","created":"2026-02-11","cited_by_count":6,"area":null},{"id":"2607.25357","title":"Raven: High-Recall Sequence Modeling with Sparse Memory Routing","created":"2026-07-28","cited_by_count":6,"area":null},{"id":"2403.18063","title":"Heracles: A Hybrid SSM-Transformer Model for High-Resolution Image and Time-Series Analysis","created":"2024-03-26","cited_by_count":5,"area":"ssm"},{"id":"2410.05448","title":"Task Diversity Shortens the ICL Plateau","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2503.22913","title":"Resona: Improving Context Copying in Linear Recurrence Models with Retrieval","created":"2025-03-28","cited_by_count":5,"area":null},{"id":"2506.03790","title":"Attention-Only Transformers via Unrolled Subspace Denoising","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2510.26912","title":"Understanding and Enhancing Mamba-Transformer Hybrids for Memory Recall and Language Modeling","created":"2025-10-30","cited_by_count":5,"area":"ssm"},{"id":"2501.01618","title":"Merging Context Clustering with Visual State Space Models for Medical Image Segmentation","created":"2025-01-03","cited_by_count":4,"area":null},{"id":"2506.18145","title":"Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection","created":"2025-06-22","cited_by_count":4,"area":"moe"},{"id":"2510.05364","title":"The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2510.14826","title":"To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models","created":"2025-10-16","cited_by_count":4,"area":null},{"id":"2603.08859","title":"Expressivity-Efficiency Tradeoffs for Hybrid Sequence Models","created":"2026-03-09","cited_by_count":4,"area":null},{"id":"2406.00209","title":"Mamba State-Space Models Are Lyapunov-Stable Learners","created":"2024-05-31","cited_by_count":3,"area":"ssm"},{"id":"2407.10347","title":"Enhancing Long-Range Dependency with State Space Model and Kolmogorov-Arnold Networks for Aspect-Based Sentiment Analysis","created":"2024-07-14","cited_by_count":3,"area":null},{"id":"2410.11687","title":"Learning in the Recurrent State: Gradient Descent with Linear Recurrent Networks","created":"2024-10-15","cited_by_count":3,"area":null},{"id":"2410.15678","title":"Revealing and Mitigating the Local Pattern Shortcuts of Mamba","created":"2024-10-21","cited_by_count":3,"area":"ssm"},{"id":"2503.12332","title":"VideoMAP: Toward Scalable Mamba-based Video Autoregressive Pretraining","created":"2025-03-16","cited_by_count":3,"area":"ssm"},{"id":"2505.11918","title":"Transformers as Unsupervised Learning Algorithms: A study on Gaussian Mixtures","created":"2025-05-17","cited_by_count":3,"area":null},{"id":"2506.09507","title":"TransXSSM: A Hybrid Transformer State Space Model with Unified Rotary Position Embedding","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2509.17514","title":"Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data","created":"2025-09-22","cited_by_count":3,"area":"ssm"},{"id":"2510.10160","title":"SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation","created":"2025-10-11","cited_by_count":3,"area":"ssm"},{"id":"2602.01651","title":"On the Spatiotemporal Dynamics of Generalization in Neural Networks","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2406.00894","title":"Pretrained Hybrids with MAD Skills","created":"2024-06-02","cited_by_count":2,"area":null},{"id":"2503.07903","title":"Can Memory-Augmented Language Models Generalize on Reasoning-in-a-Haystack Tasks?","created":"2025-03-10","cited_by_count":2,"area":"lr"},{"id":"2503.11224","title":"Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2505.06175","title":"Turbo-ICL: In-Context Learning-Based Turbo Equalization","created":"2025-05-09","cited_by_count":2,"area":null},{"id":"2510.00399","title":"How Can Mamba Learn In Context with Outliers and Generalize Provably?","created":"2025-10-01","cited_by_count":2,"area":"ssm"},{"id":"2609.04434","title":"What Attention Recalls and Recurrence Controls in Hybrid Language Models","created":"2026-09-03","cited_by_count":2,"area":"inference"},{"id":"2406.16722","title":"Venturing into Uncharted Waters: The Navigation Compass from Transformer to Mamba","created":"2024-06-24","cited_by_count":1,"area":"ssm"},{"id":"2411.01030","title":"Birdie: Advancing State Space Models with Reward-Driven Objectives and Curricula","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2412.00776","title":"Learning Mamba as a Continual Learner: Meta-Learning Selective State Space Models for Continual Learning","created":"2024-12-01","cited_by_count":1,"area":"ssm"},{"id":"2506.15176","title":"In-Context Learning for Gradient-Free Receiver Adaptation: Principles, Applications, and Theory","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2507.12442","title":"Characterizing State Space Model and Hybrid Language Model Performance with Long Context","created":"2025-07-16","cited_by_count":1,"area":null},{"id":"2510.12026","title":"Mamba Can Learn Low-Dimensional Targets In-Context via Test-Time Feature Learning","created":"2025-10-14","cited_by_count":1,"area":"ssm"},{"id":"2511.12797","title":"Genomic Next-Token Predictors are In-Context Learners","created":"2025-11-16","cited_by_count":1,"area":null},{"id":"2601.02944","title":"XLSR-MamBo: Scaling the Hybrid Mamba-Attention Backbone for Audio Deepfake Detection","created":"2026-01-06","cited_by_count":1,"area":"ssm"},{"id":"2603.12342","title":"MamTra: A Hybrid Mamba-Transformer Backbone for Speech Synthesis","created":"2026-03-12","cited_by_count":1,"area":"ssm"},{"id":"2408.10517","title":"Decision MetaMamba: Enhancing Selective SSM in Offline RL with Heterogeneous Sequence Mixing","created":"2024-08-20","cited_by_count":0,"area":"ssm"},{"id":"2408.15379","title":"DualKanbaFormer: An Efficient Selective Sparse Framework for Multimodal Aspect-based Sentiment Analysis","created":"2024-08-27","cited_by_count":0,"area":"ssm"},{"id":"2411.03945","title":"Can Custom Models Learn In-Context? An Exploration of Hybrid Architecture Performance on In-Context Learning Tasks","created":"2024-11-06","cited_by_count":0,"area":"ssm"},{"id":"2502.19787","title":"In-Context Learning with Hypothesis-Class Guidance","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2504.02013","title":"Attention Mamba: Time Series Modeling with Adaptive Pooling Acceleration and Receptive Field Enhancements","created":"2025-04-02","cited_by_count":0,"area":"ssm"},{"id":"2505.19472","title":"Balancing Computation Load and Representation Expressivity in Parallel Hybrid Neural Networks","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2601.17334","title":"Power-based Partial Attention: Bridging Linear-Complexity and Full Attention","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2602.19805","title":"Decision MetaMamba: Enhancing Selective SSM in Offline RL with Heterogeneous Sequence Mixing","created":"2026-02-23","cited_by_count":0,"area":"ssm"},{"id":"2603.29069","title":"On the Mirage of Long-Range Dependency, with an Application to Integer Multiplication","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2605.01240","title":"Rhamba: Region-Aware Hybrid Attention-Mamba Framework for Self-Supervised Learning in Resting-State fMRI","created":"2026-05-02","cited_by_count":0,"area":"ssm"},{"id":"2606.26290","title":"SSM Adapters via Hankel Reduced-order Modeling: Injection Site Determines Task Suitability in Long-Context Fine-Tuning","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.02283","title":"Dendritic In-Context Learning in a Single-Layer Spiking Neural Network","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.11614","title":"Extending LLM Context via Associative Recurrent Memory","created":"2026-07-13","cited_by_count":0,"area":null}],"next_cursor":"100"}