{"total":147,"rows":[{"id":"2412.06464","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","created":"2024-12-09","cited_by_count":532,"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":"2502.10517","title":"KernelBench: Can LLMs Write Efficient GPU Kernels?","created":"2025-02-14","cited_by_count":225,"area":null},{"id":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146,"area":null},{"id":"2404.07904","title":"HGRN2: Gated Linear RNNs with State Expansion","created":"2024-04-11","cited_by_count":127,"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":"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":"2505.23735","title":"ATLAS: Learning to Optimally Memorize the Context at Test Time","created":"2025-05-29","cited_by_count":66,"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":"2506.04761","title":"Log-Linear Attention","created":"2025-06-05","cited_by_count":40,"area":null},{"id":"2410.20399","title":"ThunderKittens: Simple, Fast, and Adorable AI Kernels","created":"2024-10-27","cited_by_count":36,"area":null},{"id":"2505.16381","title":"PaTH Attention: Position Encoding via Accumulating Householder Transformations","created":"2025-05-22","cited_by_count":34,"area":null},{"id":"2503.01496","title":"Liger: Linearizing Large Language Models to Gated Recurrent Structures","created":"2025-03-03","cited_by_count":33,"area":null},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"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":"2508.21141","title":"Adaptive LLM Routing under Budget Constraints","created":"2025-08-28","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":"2411.10741","title":"MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map","created":"2024-11-16","cited_by_count":21,"area":null},{"id":"2512.20569","title":"Distilling to Hybrid Attention Models via KL-Guided Layer Selection","created":"2025-12-23","cited_by_count":20,"area":null},{"id":"2504.05646","title":"Lattice: Learning to Efficiently Compress the Memory","created":"2025-04-08","cited_by_count":19,"area":null},{"id":"2411.12892","title":"Selective Attention: Enhancing Transformer through Principled Context Control","created":"2024-11-19","cited_by_count":16,"area":null},{"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":"2602.24281","title":"Memory Caching: RNNs with Growing Memory","created":"2026-02-27","cited_by_count":15,"area":null},{"id":"2405.18425","title":"ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention","created":"2024-05-28","cited_by_count":13,"area":null},{"id":"2408.04093","title":"Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters","created":"2024-08-07","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":"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":"2509.24552","title":"Short window attention enables long-term memorization","created":"2025-09-29","cited_by_count":11,"area":null},{"id":"2506.15545","title":"RATTENTION: Towards the Minimal Sliding Window Size in Local-Global Attention Models","created":"2025-06-18","cited_by_count":10,"area":null},{"id":"2510.07019","title":"Native Hybrid Attention for Efficient Sequence Modeling","created":"2025-10-08","cited_by_count":10,"area":null},{"id":"2501.14577","title":"ZETA: Leveraging Z-order Curves for Efficient Top-k Attention","created":"2025-01-24","cited_by_count":9,"area":null},{"id":"2503.03588","title":"PowerAttention: Exponentially Scaling of Receptive Fields for Effective Sparse Attention","created":"2025-03-05","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":"2607.07386","title":"Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity","created":"2026-07-08","cited_by_count":9,"area":null},{"id":"2508.19029","title":"Revisiting associative recall in modern recurrent models","created":"2025-08-26","cited_by_count":8,"area":null},{"id":"2511.07343","title":"TNT: Improving Chunkwise Training for Test-Time Memorization","created":"2025-11-10","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":"2411.17800","title":"STAR: Synthesis of Tailored Architectures","created":"2024-11-26","cited_by_count":7,"area":null},{"id":"2604.21100","title":"Preconditioned DeltaNet: Curvature-aware Sequence Modeling for Linear Recurrences","created":"2026-04-22","cited_by_count":7,"area":null},{"id":"2605.20670","title":"LT2: Linear-Time Looped Transformers","created":"2026-05-20","cited_by_count":7,"area":null},{"id":"2407.05591","title":"On the Power of Convolution Augmented Transformer","created":"2024-07-08","cited_by_count":6,"area":null},{"id":"2410.06577","title":"Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2507.09025","title":"Lizard: An Efficient Linearization Framework for Large Language Models","created":"2025-07-11","cited_by_count":6,"area":null},{"id":"2602.04852","title":"On State Reduction in Linear Attention","created":"2026-02-04","cited_by_count":6,"area":null},{"id":"2602.11374","title":"Retrieval-Aware Distillation for Transformer-SSM Hybrids","created":"2026-02-11","cited_by_count":6,"area":null},{"id":"2607.02303","title":"A Hippocampus for Linear Attention: An Exact Memory for What the Recurrent State Forgets","created":"2026-07-02","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":"2509.05276","title":"SpikingBrain: Spiking Brain-inspired Large Models","created":"2025-09-05","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":"2606.10650","title":"Dynamic Linear Attention","created":"2026-06-09","cited_by_count":5,"area":null},{"id":"2502.16249","title":"Linear Attention for Efficient Bidirectional Sequence Modeling","created":"2025-02-22","cited_by_count":4,"area":null},{"id":"2504.00492","title":"ParallelFlow: Parallelizing Linear Transformers via Flow Discretization","created":"2025-04-01","cited_by_count":4,"area":null},{"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":"2607.14144","title":"The Capability Convergence Hypothesis: Capability from Access Structure, Not Scale","created":"2026-07-14","cited_by_count":4,"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":"2507.04239","title":"Scaling Context Requires Rethinking Attention","created":"2025-07-06","cited_by_count":3,"area":null},{"id":"2509.09001","title":"Fast attention mechanisms: a tale of parallelism","created":"2025-09-10","cited_by_count":3,"area":null},{"id":"2511.05313","title":"Controllably Efficient Language Models","created":"2025-11-07","cited_by_count":3,"area":null},{"id":"2601.11667","title":"Distill-then-Replace: Efficient Task-Specific Hybrid Attention Model Construction","created":"2026-01-16","cited_by_count":3,"area":null},{"id":"2602.02195","title":"State Rank Dynamics in Linear Attention LLMs","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2602.03681","title":"Neural Attention Search Linear: Towards Adaptive Token-Level Hybrid Attention Models","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2602.13215","title":"When to Think Fast and Slow? AMOR: Adaptive Entropy Gate for Hybrid Models","created":"2026-01-22","cited_by_count":3,"area":null},{"id":"2603.15590","title":"Effective Distillation to Hybrid xLSTM Architectures","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2607.17419","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","created":"2026-07-19","cited_by_count":3,"area":null},{"id":"2609.02986","title":"Modern Transformers Are Implicit Hybrids: From Functional Differentiation to Principled Hybrid Architecture Design","created":"2026-09-02","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":"2409.14595","title":"EchoAtt: Attend, Copy, then Adjust for More Efficient Large Language Models","created":"2024-09-22","cited_by_count":2,"area":null},{"id":"2410.12850","title":"RecurFormer: Not All Transformer Heads Need Self-Attention","created":"2024-10-10","cited_by_count":2,"area":null},{"id":"2510.11602","title":"Deconstructing Attention: Investigating Design Principles for Effective Language Modeling","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2512.11411","title":"Sliced ReLU attention: Quasi-linear contextual expressivity via sorting","created":"2025-12-12","cited_by_count":2,"area":null},{"id":"2601.22563","title":"EUGens: Efficient, Unified, and General Dense Layers","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2602.11958","title":"RAM-Net: Linear-Time Sequence Modeling with Sparsely Addressable State","created":"2026-02-12","cited_by_count":2,"area":null},{"id":"2604.22575","title":"SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2606.01294","title":"Don't Read Everything: A Curvature-Conditioned Query for Linear Attention","created":"2026-05-31","cited_by_count":2,"area":null},{"id":"2606.03979","title":"Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2606.30562","title":"Morphing into Hybrid Attention Models","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2608.12435","title":"MARCH: Scaling Recurrent Memory with Content-Routed State Anchors","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2410.23320","title":"Lina-Speech: Gated Linear Attention and Initial-State Tuning for Multi-Sample Prompting Text-To-Speech Synthesis","created":"2024-10-30","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":"2501.13428","title":"Softplus Attention with Re-weighting Boosts Length Extrapolation in Large Language Models","created":"2025-01-23","cited_by_count":1,"area":null},{"id":"2509.05282","title":"Elucidating the Design Space of Decay in Linear Attention","created":"2025-09-05","cited_by_count":1,"area":null},{"id":"2509.22630","title":"StateX: Enhancing RNN Recall via Post-training State Expansion","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2510.09389","title":"Design Principles for Sequence Models via Coefficient Dynamics","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2510.21956","title":"Transformer Based Linear Attention with Optimized GPU Kernel Implementation","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2511.00576","title":"FlashEVA: Accelerating LLM inference via Efficient Attention","created":"2025-11-01","cited_by_count":1,"area":null},{"id":"2512.13921","title":"Sliding Window Recurrences for Sequence Models","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2601.13352","title":"LLM-as-RNN: A Recurrent Language Model for Memory Updates and Sequence Prediction","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2602.01744","title":"Softmax Linear Attention: Reclaiming Global Competition","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.04915","title":"SLAY: Geometry-Aware Spherical Linearized Attention with Yat-Kernel","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2603.22325","title":"Hybrid Associative Memories","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2605.05066","title":"The Impossibility Triangle of Long-Context Modeling","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.13473","title":"OSDN: Improving Delta Rule with Provable Online Preconditioning in Linear Attention","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.28769","title":"Multi-Mixer Models: Flexible Sequence Modeling with Shared Representations","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.27748","title":"Flexformer: Flexible Linear Transformer with Learnable Attention Kernel","created":"2026-06-26","cited_by_count":1,"area":null}],"next_cursor":"100"}