{"total":1411,"rows":[{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673,"area":null},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455,"area":null},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984,"area":null},{"id":"2404.06654","title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","created":"2024-04-09","cited_by_count":1346,"area":null},{"id":"2210.02186","title":"TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis","created":"2022-10-05","cited_by_count":1058,"area":null},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969,"area":null},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827,"area":null},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713,"area":null},{"id":"2302.11939","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","created":"2023-02-23","cited_by_count":632,"area":null},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613,"area":null},{"id":"2412.06464","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","created":"2024-12-09","cited_by_count":532,"area":null},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525,"area":null},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499,"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":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408,"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":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393,"area":null},{"id":"2407.02490","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","created":"2024-07-02","cited_by_count":383,"area":null},{"id":"2304.08424","title":"Long-term Forecasting with TiDE: Time-series Dense Encoder","created":"2023-04-17","cited_by_count":332,"area":null},{"id":"2309.16039","title":"Effective Long-Context Scaling of Foundation Models","created":"2023-09-27","cited_by_count":303,"area":null},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265,"area":null},{"id":"2402.19427","title":"Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models","created":"2024-02-29","cited_by_count":242,"area":null},{"id":"2303.06053","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","created":"2023-03-10","cited_by_count":240,"area":null},{"id":"2402.01032","title":"Repeat After Me: Transformers are Better than State Space Models at Copying","created":"2024-02-01","cited_by_count":216,"area":null},{"id":"2307.02486","title":"LongNet: Scaling Transformers to 1,000,000,000 Tokens","created":"2023-07-05","cited_by_count":204,"area":null},{"id":"2208.09399","title":"Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models","created":"2022-08-19","cited_by_count":198,"area":null},{"id":"2407.13278","title":"Deep Time Series Models: A Comprehensive Survey and Benchmark","created":"2024-07-18","cited_by_count":197,"area":null},{"id":"2306.15794","title":"HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution","created":"2023-06-27","cited_by_count":194,"area":null},{"id":"2210.06774","title":"Re3: Generating Longer Stories With Recursive Reprompting and Revision","created":"2022-10-13","cited_by_count":193,"area":null},{"id":"2402.17152","title":"Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations","created":"2024-02-27","cited_by_count":188,"area":null},{"id":"2404.08819","title":"The Illusion of State in State-Space Models","created":"2024-04-12","cited_by_count":187,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179,"area":null},{"id":"2405.14782","title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","created":"2024-05-23","cited_by_count":179,"area":null},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178,"area":null},{"id":"2202.09729","title":"It's Raw! Audio Generation with State-Space Models","created":"2022-02-20","cited_by_count":171,"area":null},{"id":"2305.07185","title":"MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers","created":"2023-05-12","cited_by_count":170,"area":null},{"id":"2404.05892","title":"Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence","created":"2024-04-08","cited_by_count":159,"area":null},{"id":"2205.08897","title":"FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting","created":"2022-05-18","cited_by_count":147,"area":null},{"id":"2306.09364","title":"TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting","created":"2023-06-14","cited_by_count":139,"area":null},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136,"area":null},{"id":"2404.07904","title":"HGRN2: Gated Linear RNNs with State Expansion","created":"2024-04-11","cited_by_count":127,"area":null},{"id":"2405.16712","title":"Zamba: A Compact 7B SSM Hybrid Model","created":"2024-05-26","cited_by_count":124,"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":"2402.04347","title":"The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry","created":"2024-02-06","cited_by_count":120,"area":null},{"id":"2504.08528","title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","created":"2025-04-11","cited_by_count":118,"area":null},{"id":"2410.16032","title":"TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis","created":"2024-10-21","cited_by_count":116,"area":null},{"id":"2410.12781","title":"Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats","created":"2024-10-16","cited_by_count":114,"area":null},{"id":"2403.03234","title":"Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling","created":"2024-03-05","cited_by_count":113,"area":null},{"id":"2403.08540","title":"Language models scale reliably with over-training and on downstream tasks","created":"2024-03-13","cited_by_count":113,"area":null},{"id":"2403.07300","title":"CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning","created":"2024-03-12","cited_by_count":108,"area":null},{"id":"2204.01692","title":"Long Movie Clip Classification with State-Space Video Models","created":"2022-04-04","cited_by_count":106,"area":null},{"id":"2311.04823","title":"Hierarchically Gated Recurrent Neural Network for Sequence Modeling","created":"2023-11-08","cited_by_count":102,"area":null},{"id":"2411.13676","title":"Hymba: A Hybrid-head Architecture for Small Language Models","created":"2024-11-20","cited_by_count":99,"area":null},{"id":"2304.11062","title":"Scaling Transformer to 1M tokens and beyond with RMT","created":"2023-04-19","cited_by_count":98,"area":null},{"id":"2403.02308","title":"Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures","created":"2024-03-04","cited_by_count":98,"area":null},{"id":"2403.00131","title":"UniTS: A Unified Multi-Task Time Series Model","created":"2024-02-29","cited_by_count":94,"area":null},{"id":"2405.19707","title":"DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark","created":"2024-05-30","cited_by_count":92,"area":null},{"id":"2403.11423","title":"VmambaIR: Visual State Space Model for Image Restoration","created":"2024-03-18","cited_by_count":90,"area":null},{"id":"2506.09350","title":"Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation","created":"2025-06-11","cited_by_count":90,"area":null},{"id":"2401.12973","title":"In-Context Language Learning: Architectures and Algorithms","created":"2024-01-23","cited_by_count":89,"area":null},{"id":"2410.10306","title":"Animate-X: Universal Character Image Animation with Enhanced Motion Representation","created":"2024-10-14","cited_by_count":88,"area":null},{"id":"2210.09298","title":"What Makes Convolutional Models Great on Long Sequence Modeling?","created":"2022-10-17","cited_by_count":87,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2402.02399","title":"FreDF: Learning to Forecast in the Frequency Domain","created":"2024-02-04","cited_by_count":79,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2402.15584","title":"State Space Models for Event Cameras","created":"2024-02-23","cited_by_count":75,"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":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72,"area":null},{"id":"2507.07955","title":"Dynamic Chunking for End-to-End Hierarchical Sequence Modeling","created":"2025-07-10","cited_by_count":72,"area":null},{"id":"2208.00748","title":"Efficient Long-Text Understanding with Short-Text Models","created":"2022-08-01","cited_by_count":71,"area":null},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2403.13724","title":"Probabilistic Forecasting with Stochastic Interpolants and F\\\"ollmer Processes","created":"2024-03-20","cited_by_count":66,"area":null},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65,"area":null},{"id":"2402.18510","title":"RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval","created":"2024-02-28","cited_by_count":64,"area":null},{"id":"2404.07839","title":"RecurrentGemma: Moving Past Transformers for Efficient Open Language Models","created":"2024-04-11","cited_by_count":64,"area":null},{"id":"2504.13173","title":"It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization","created":"2025-04-17","cited_by_count":64,"area":null},{"id":"2402.10635","title":"ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling","created":"2024-02-16","cited_by_count":63,"area":null},{"id":"2302.06646","title":"Simple Hardware-Efficient Long Convolutions for Sequence Modeling","created":"2023-02-13","cited_by_count":62,"area":null},{"id":"2303.01859","title":"POPGym: Benchmarking Partially Observable Reinforcement Learning","created":"2023-03-03","cited_by_count":62,"area":null},{"id":"2405.14174","title":"Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model","created":"2024-05-23","cited_by_count":62,"area":null},{"id":"2202.07765","title":"General-purpose, long-context autoregressive modeling with Perceiver AR","created":"2022-02-15","cited_by_count":60,"area":null},{"id":"2409.07431","title":"Synthetic continued pretraining","created":"2024-09-11","cited_by_count":60,"area":null},{"id":"2403.17844","title":"Mechanistic Design and Scaling of Hybrid Architectures","created":"2024-03-26","cited_by_count":59,"area":null},{"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":"2402.04059","title":"Deep Learning for Multivariate Time Series Imputation: A Survey","created":"2024-02-06","cited_by_count":57,"area":null},{"id":"2305.12095","title":"CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting","created":"2023-05-20","cited_by_count":55,"area":null},{"id":"2303.09489","title":"Effectively Modeling Time Series with Simple Discrete State Spaces","created":"2023-03-16","cited_by_count":54,"area":null},{"id":"2309.13345","title":"BAMBOO: A Comprehensive Benchmark for Evaluating Long Text Modeling Capacities of Large Language Models","created":"2023-09-23","cited_by_count":53,"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":"2406.16747","title":"Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers","created":"2024-06-24","cited_by_count":52,"area":null},{"id":"2212.10544","title":"Pretraining Without Attention","created":"2022-12-20","cited_by_count":51,"area":null},{"id":"2212.14427","title":"Efficient Movie Scene Detection using State-Space Transformers","created":"2022-12-29","cited_by_count":51,"area":null},{"id":"2405.06640","title":"Linearizing Large Language Models","created":"2024-05-10","cited_by_count":51,"area":null},{"id":"2406.04303","title":"Vision-LSTM: xLSTM as Generic Vision Backbone","created":"2024-06-06","cited_by_count":51,"area":null},{"id":"2405.16105","title":"MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space","created":"2024-05-25","cited_by_count":48,"area":null},{"id":"2408.10920","title":"Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations","created":"2024-08-20","cited_by_count":47,"area":null},{"id":"2501.18795","title":"Rope to Nope and Back Again: A New Hybrid Attention Strategy","created":"2025-01-30","cited_by_count":47,"area":null},{"id":"2502.13685","title":"MoM: Linear Sequence Modeling with Mixture-of-Memories","created":"2025-02-19","cited_by_count":47,"area":null}],"next_cursor":"100"}