{"total":27,"rows":[{"id":"2402.05099","title":"Hydragen: High-Throughput LLM Inference with Shared Prefixes","created":"2024-02-07","cited_by_count":73,"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":"2404.08763","title":"CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models","created":"2024-04-12","cited_by_count":41,"area":null},{"id":"2410.20399","title":"ThunderKittens: Simple, Fast, and Adorable AI Kernels","created":"2024-10-27","cited_by_count":36,"area":null},{"id":"2405.06147","title":"State-Free Inference of State-Space Models: The Transfer Function Approach","created":"2024-05-10","cited_by_count":18,"area":null},{"id":"2405.07518","title":"SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts","created":"2024-05-13","cited_by_count":18,"area":null},{"id":"2406.00943","title":"State Space Models on Temporal Graphs: A First-Principles Study","created":"2024-06-03","cited_by_count":16,"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":"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":"2409.10489","title":"Flash STU: Fast Spectral Transform Units","created":"2024-09-16","cited_by_count":7,"area":null},{"id":"2402.18508","title":"Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling","created":"2024-02-28","cited_by_count":6,"area":null},{"id":"2405.17383","title":"Unlocking the Secrets of Linear Complexity Sequence Model from A Unified Perspective","created":"2024-05-27","cited_by_count":6,"area":null},{"id":"2407.01049","title":"SE(3)-Hyena Operator for Scalable Equivariant Learning","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2411.03527","title":"PACE: Pacing Operator Learning to Accurate Optical Field Simulation for Complicated Photonic Devices","created":"2024-11-05","cited_by_count":5,"area":null},{"id":"2403.03772","title":"AcceleratedLiNGAM: Learning Causal DAGs at the speed of GPUs","created":"2024-03-06","cited_by_count":4,"area":null},{"id":"2410.12389","title":"A Fast Convoluted Story: Scaling Probabilistic Inference for Integer Arithmetic","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2410.12982","title":"Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond","created":"2024-10-16","cited_by_count":3,"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":"2510.22673","title":"Alias-Free ViT: Fractional Shift Invariance via Linear Attention","created":"2025-10-26","cited_by_count":2,"area":null},{"id":"2408.11200","title":"Want to train KANS at scale? Now UKAN!","created":"2024-08-20","cited_by_count":1,"area":null},{"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":"2606.26421","title":"Otter Weather: Skillful and Computationally Efficient Medium-Range Weather Forecasting","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2606.26439","title":"TileMaxSim: IO-Aware GPU MaxSim Scoring with Dimension Tiling and Fused Product Quantization","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2601.06065","title":"Enabling Long FFT Convolutions on Memory-Constrained FPGAs via Chunking","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2605.08451","title":"RubiConv -- Efficient Boundary-Respecting Convolutions","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2607.19378","title":"Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2609.24089","title":"FlashBoB: I/O-Efficient Exact Backward-over-Backward for Softmax Attention","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}