{"total":251,"rows":[{"id":"2412.06464","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","created":"2024-12-09","cited_by_count":532,"area":null},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519,"area":null},{"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":"2405.05254","title":"You Only Cache Once: Decoder-Decoder Architectures for Language Models","created":"2024-05-08","cited_by_count":144,"area":null},{"id":"2509.26645","title":"TTT3R: 3D Reconstruction as Test-Time Training","created":"2025-09-30","cited_by_count":129,"area":null},{"id":"2502.20766","title":"FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference","created":"2025-02-28","cited_by_count":123,"area":null},{"id":"2505.23719","title":"TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning","created":"2025-05-29","cited_by_count":120,"area":null},{"id":"2405.20853","title":"MeshXL: Neural Coordinate Field for Generative 3D Foundation Models","created":"2024-05-31","cited_by_count":103,"area":null},{"id":"2502.10297","title":"DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products","created":"2025-02-14","cited_by_count":75,"area":null},{"id":"2501.12352","title":"Test-time regression: a unifying framework for designing sequence models with associative memory","created":"2025-01-21","cited_by_count":74,"area":null},{"id":"2512.24695","title":"Nested Learning: The Illusion of Deep Learning Architectures","created":"2025-12-31","cited_by_count":72,"area":null},{"id":"2503.02130","title":"Forgetting Transformer: Softmax Attention with a Forget Gate","created":"2025-03-03","cited_by_count":53,"area":null},{"id":"2502.13685","title":"MoM: Linear Sequence Modeling with Mixture-of-Memories","created":"2025-02-19","cited_by_count":47,"area":null},{"id":"2506.05233","title":"MesaNet: Sequence Modeling by Locally Optimal Test-Time Training","created":"2025-06-05","cited_by_count":47,"area":null},{"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":"2502.12671","title":"Baichuan-M1: Pushing the Medical Capability of Large Language Models","created":"2025-02-18","cited_by_count":43,"area":null},{"id":"2506.04761","title":"Log-Linear Attention","created":"2025-06-05","cited_by_count":40,"area":null},{"id":"2407.19115","title":"Towards Scalable and Stable Parallelization of Nonlinear RNNs","created":"2024-07-26","cited_by_count":38,"area":null},{"id":"2410.01201","title":"Were RNNs All We Needed?","created":"2024-10-02","cited_by_count":38,"area":null},{"id":"2405.14722","title":"DAPE: Data-Adaptive Positional Encoding for Length Extrapolation","created":"2024-05-23","cited_by_count":31,"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":"2605.20119","title":"Toto 2.0: Time Series Forecasting Enters the Scaling Era","created":"2026-05-19","cited_by_count":30,"area":null},{"id":"2410.10254","title":"LoLCATs: On Low-Rank Linearizing of Large Language Models","created":"2024-10-14","cited_by_count":27,"area":null},{"id":"2405.15731","title":"Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks","created":"2024-05-24","cited_by_count":26,"area":null},{"id":"2407.06324","title":"B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory","created":"2024-07-08","cited_by_count":26,"area":null},{"id":"2502.15637","title":"Mantis: Lightweight Foundation Model for Time Series Classification","created":"2025-02-21","cited_by_count":24,"area":null},{"id":"2503.01835","title":"Primus: Enforcing Attention Usage for 3D Medical Image Segmentation","created":"2025-03-03","cited_by_count":24,"area":null},{"id":"2507.02782","title":"Understanding and Improving Length Generalization in Recurrent Models","created":"2025-07-03","cited_by_count":23,"area":null},{"id":"2507.19595","title":"Efficient Attention Mechanisms for Large Language Models: A Survey","created":"2025-07-25","cited_by_count":22,"area":null},{"id":"2407.12327","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","created":"2024-07-17","cited_by_count":21,"area":null},{"id":"2410.16928","title":"xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories","created":"2024-10-22","cited_by_count":19,"area":null},{"id":"2504.05646","title":"Lattice: Learning to Efficiently Compress the Memory","created":"2025-04-08","cited_by_count":19,"area":null},{"id":"2503.13427","title":"xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference","created":"2025-03-17","cited_by_count":18,"area":null},{"id":"2505.17761","title":"Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models","created":"2025-05-23","cited_by_count":18,"area":null},{"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":"2510.25502","title":"TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting","created":"2025-10-29","cited_by_count":17,"area":null},{"id":"2501.11587","title":"Recurrent Diffusion for Large-Scale Parameter Generation","created":"2025-01-20","cited_by_count":15,"area":null},{"id":"2506.02475","title":"Comba: Improving Bilinear RNNs with Closed-loop Control","created":"2025-06-03","cited_by_count":15,"area":null},{"id":"2407.10240","title":"xLSTMTime : Long-term Time Series Forecasting With xLSTM","created":"2024-07-14","cited_by_count":14,"area":null},{"id":"2409.13265","title":"Towards LifeSpan Cognitive Systems","created":"2024-09-20","cited_by_count":13,"area":null},{"id":"2411.04165","title":"Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences","created":"2024-11-06","cited_by_count":13,"area":null},{"id":"2503.14376","title":"Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels","created":"2025-03-18","cited_by_count":13,"area":null},{"id":"2507.12549","title":"The Serial Scaling Hypothesis","created":"2025-07-16","cited_by_count":13,"area":null},{"id":"2507.16577","title":"Scaling Linear Attention with Sparse State Expansion","created":"2025-07-22","cited_by_count":13,"area":null},{"id":"2602.17634","title":"Reverso: Efficient Time Series Foundation Models for Zero-shot Forecasting","created":"2026-02-19","cited_by_count":13,"area":null},{"id":"2607.01204","title":"TiRex-2: Generalizing TiRex to Multivariate Data and Streaming","created":"2026-07-01","cited_by_count":13,"area":null},{"id":"2503.01868","title":"Systems and Algorithms for Convolutional Multi-Hybrid Language Models at Scale","created":"2025-02-25","cited_by_count":12,"area":null},{"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":"2505.23666","title":"LoLA: Low-Rank Linear Attention With Sparse Caching","created":"2025-05-29","cited_by_count":12,"area":null},{"id":"2506.00744","title":"Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers","created":"2025-05-31","cited_by_count":12,"area":null},{"id":"2602.06909","title":"Revisiting the Generic Transformer: Deconstructing a Strong Baseline for Time Series Foundation Models","created":"2026-02-06","cited_by_count":12,"area":null},{"id":"2409.19315","title":"Analog In-Memory Computing Attention Mechanism for Fast and Energy-Efficient Large Language Models","created":"2024-09-28","cited_by_count":11,"area":null},{"id":"2510.07318","title":"Artificial Hippocampus Networks for Efficient Long-Context Modeling","created":"2025-10-08","cited_by_count":11,"area":null},{"id":"2602.17868","title":"MantisV2: Closing the Zero-Shot Gap in Time Series Classification with Synthetic Data and Test-Time Strategies","created":"2026-02-19","cited_by_count":11,"area":null},{"id":"2407.09946","title":"Low-Rank Interconnected Adaptation across Layers","created":"2024-07-13","cited_by_count":10,"area":null},{"id":"2410.04798","title":"DAPE V2: Process Attention Score as Feature Map for Length Extrapolation","created":"2024-10-07","cited_by_count":10,"area":null},{"id":"2505.18728","title":"Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling","created":"2025-05-24","cited_by_count":10,"area":null},{"id":"2410.01651","title":"Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling","created":"2024-10-02","cited_by_count":9,"area":null},{"id":"2503.04725","title":"L$^2$M: Mutual Information Scaling Law for Long-Context Language Modeling","created":"2025-03-06","cited_by_count":9,"area":null},{"id":"2504.12959","title":"Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Prediction","created":"2025-04-17","cited_by_count":9,"area":null},{"id":"2509.10151","title":"BenchECG and xECG: a benchmark and baseline for ECG foundation models","created":"2025-09-12","cited_by_count":9,"area":null},{"id":"2510.26777","title":"Pre-trained Forecasting Models: Strong Zero-Shot Feature Extractors for Time Series Classification","created":"2025-10-30","cited_by_count":9,"area":null},{"id":"2511.17388","title":"Selective Rotary Position Embedding","created":"2025-11-21","cited_by_count":9,"area":null},{"id":"2502.14045","title":"There are no Champions in Supervised Long-Term Time Series Forecasting","created":"2025-02-19","cited_by_count":8,"area":null},{"id":"2508.05287","title":"FlowState: Sampling-Rate-Equivariant Time-Series Forecasting","created":"2025-08-07","cited_by_count":8,"area":null},{"id":"2508.08435","title":"Fast weight programming and linear transformers: from machine learning to neurobiology","created":"2025-08-11","cited_by_count":8,"area":null},{"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,"area":null},{"id":"2603.03612","title":"Why Are Linear RNNs More Parallelizable?","created":"2026-03-04","cited_by_count":8,"area":null},{"id":"2603.14360","title":"M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling","created":"2026-03-15","cited_by_count":8,"area":null},{"id":"2410.06718","title":"MatMamba: A Matryoshka State Space Model","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2410.10047","title":"ChangeMinds: Multi-task Framework for Detecting and Describing Changes in Remote Sensing","created":"2024-10-13","cited_by_count":7,"area":null},{"id":"2412.07752","title":"FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware","created":"2024-12-10","cited_by_count":7,"area":null},{"id":"2411.15671","title":"Best of Both Worlds: Advantages of Hybrid Graph Sequence Models","created":"2024-11-23","cited_by_count":6,"area":null},{"id":"2412.08604","title":"Preference Discerning with LLM-Enhanced Generative Retrieval","created":"2024-12-11","cited_by_count":6,"area":null},{"id":"2412.14847","title":"A Survey of RWKV","created":"2024-12-19","cited_by_count":6,"area":null},{"id":"2506.22837","title":"xLSTMAD: A Powerful xLSTM-based Method for Anomaly Detection","created":"2025-06-28","cited_by_count":6,"area":null},{"id":"2510.07151","title":"ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL Problems","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2511.21622","title":"On the Origin of Algorithmic Progress in AI","created":"2025-11-26","cited_by_count":6,"area":null},{"id":"2602.14814","title":"Learning State-Tracking from Code Using Linear RNNs","created":"2026-02-16","cited_by_count":6,"area":null},{"id":"2605.26797","title":"Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior","created":"2026-05-26","cited_by_count":6,"area":null},{"id":"2406.14086","title":"Seg-LSTM: Performance of xLSTM for Semantic Segmentation of Remotely Sensed Images","created":"2024-06-20","cited_by_count":5,"area":null},{"id":"2410.10101","title":"Learning Linear Attention in Polynomial Time","created":"2024-10-14","cited_by_count":5,"area":null},{"id":"2412.14294","title":"TRecViT: A Recurrent Video Transformer","created":"2024-12-18","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":"2506.01153","title":"Weight-Space Linear Recurrent Neural Networks","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2507.03285","title":"Memory Mosaics at scale","created":"2025-07-04","cited_by_count":5,"area":null},{"id":"2512.23852","title":"Trellis: Learning to Compress Key-Value Memory in Attention Models","created":"2025-12-29","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":"2411.05636","title":"Video RWKV:Video Action Recognition Based RWKV","created":"2024-11-08","cited_by_count":4,"area":null},{"id":"2411.07863","title":"CDXLSTM: Boosting Remote Sensing Change Detection with Extended Long Short-Term Memory","created":"2024-11-12","cited_by_count":4,"area":null},{"id":"2411.16346","title":"Towards Foundation Models for Critical Care Time Series","created":"2024-11-25","cited_by_count":4,"area":null},{"id":"2501.14256","title":"DKT2: Revisiting Applicable and Comprehensive Knowledge Tracing in Large-Scale Data","created":"2025-01-24","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":"2502.10760","title":"Why is prompting hard? Understanding prompts on binary sequence predictors","created":"2025-02-15","cited_by_count":4,"area":null},{"id":"2502.16249","title":"Linear Attention for Efficient Bidirectional Sequence Modeling","created":"2025-02-22","cited_by_count":4,"area":null},{"id":"2505.21749","title":"Revisiting Bi-Linear State Transitions in Recurrent Neural Networks","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2506.15881","title":"T-SHRED: Symbolic Regression for Regularization and Model Discovery with Transformer Shallow Recurrent Decoders","created":"2025-06-18","cited_by_count":4,"area":null},{"id":"2509.21716","title":"A Unifying Framework for Parallelizing Sequential Models with Linear Dynamical Systems","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2602.16864","title":"Position: A Dynamical Systems Perspective is Needed to Advance Time Series Modeling","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2605.05602","title":"Nearly Optimal Attention Coresets","created":"2026-05-07","cited_by_count":4,"area":null}],"next_cursor":"100"}