{"total":75,"rows":[{"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":"2411.13676","title":"Hymba: A Hybrid-head Architecture for Small Language Models","created":"2024-11-20","cited_by_count":99,"area":null},{"id":"2410.20672","title":"Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA","created":"2024-10-28","cited_by_count":78,"area":null},{"id":"2505.01618","title":"Don't be lazy: CompleteP enables compute-efficient deep transformers","created":"2025-05-02","cited_by_count":78,"area":null},{"id":"2507.06457","title":"A Systematic Analysis of Hybrid Linear Attention","created":"2025-07-08","cited_by_count":39,"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":"2411.19379","title":"Marconi: Prefix Caching for the Era of Hybrid LLMs","created":"2024-11-28","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":"2412.15285","title":"Maximize Your Data's Potential: Enhancing LLM Accuracy with Two-Phase Pretraining","created":"2024-12-18","cited_by_count":26,"area":null},{"id":"2411.15242","title":"The Zamba2 Suite: Technical Report","created":"2024-11-22","cited_by_count":21,"area":null},{"id":"2510.06826","title":"Mid-Training of Large Language Models: A Survey","created":"2025-10-08","cited_by_count":21,"area":null},{"id":"2412.18603","title":"Long-Form Speech Generation with Spoken Language Models","created":"2024-12-24","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":"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":"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":"2411.06068","title":"Zyda-2: a 5 Trillion Token High-Quality Dataset","created":"2024-11-09","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":"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":"2505.23666","title":"LoLA: Low-Rank Linear Attention With Sparse Caching","created":"2025-05-29","cited_by_count":12,"area":null},{"id":"2412.13328","title":"Expansion Span: Combining Fading Memory and Retrieval in Hybrid State Space Models","created":"2024-12-17","cited_by_count":11,"area":null},{"id":"2511.21016","title":"Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression","created":"2025-11-26","cited_by_count":11,"area":null},{"id":"2510.07019","title":"Native Hybrid Attention for Efficient Sequence Modeling","created":"2025-10-08","cited_by_count":10,"area":null},{"id":"2406.16135","title":"Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models","created":"2024-06-23","cited_by_count":9,"area":null},{"id":"2502.10807","title":"HybriDNA: A Hybrid Transformer-Mamba2 Long-Range DNA Language Model","created":"2025-02-15","cited_by_count":7,"area":null},{"id":"2504.11409","title":"Minitron-SSM: Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning","created":"2025-04-15","cited_by_count":7,"area":null},{"id":"2504.03101","title":"Single-Pass Document Scanning for Question Answering","created":"2025-04-04","cited_by_count":6,"area":null},{"id":"2504.21463","title":"RWKV-X: A Linear Complexity Hybrid Language Model","created":"2025-04-30","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":"2510.17196","title":"Understanding and Improving Length Generalization in Hierarchical Sparse Attention Models","created":"2025-10-20","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":"2606.01774","title":"FLARE: Diffusion for Hybrid Language Model","created":"2026-06-01","cited_by_count":6,"area":null},{"id":"2502.13785","title":"Helix-mRNA: A Hybrid Foundation Model For Full Sequence mRNA Therapeutics","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2509.05276","title":"SpikingBrain: Spiking Brain-inspired Large Models","created":"2025-09-05","cited_by_count":5,"area":null},{"id":"2601.17367","title":"Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers","created":"2026-01-24","cited_by_count":5,"area":null},{"id":"2602.11534","title":"Krause Synchronization Transformers","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2605.08301","title":"Priming: Hybrid State Space Models From Pre-trained Transformers","created":"2026-05-08","cited_by_count":5,"area":null},{"id":"2407.12220","title":"Questionable practices in machine learning","created":"2024-07-17","cited_by_count":4,"area":null},{"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":"2607.14144","title":"The Capability Convergence Hypothesis: Capability from Access Structure, Not Scale","created":"2026-07-14","cited_by_count":4,"area":null},{"id":"2406.01981","title":"Zyda: A 1.3T Dataset for Open Language Modeling","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2506.09316","title":"On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2508.18387","title":"Integral Transformer: Denoising Attention, Not Too Much Not Too Little","created":"2025-08-25","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":"2601.22379","title":"SPLA: Block Sparse Plus Linear Attention for Long Context Modeling","created":"2026-01-29","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":"2408.12963","title":"Open Llama2 Model for the Lithuanian Language","created":"2024-08-23","cited_by_count":2,"area":null},{"id":"2501.05465","title":"Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)","created":"2025-01-03","cited_by_count":2,"area":null},{"id":"2501.13230","title":"Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions","created":"2025-01-22","cited_by_count":2,"area":null},{"id":"2502.17873","title":"An Efficient Self-Supervised Framework for Long-Sequence EEG Modeling","created":"2025-02-25","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":"2604.13440","title":"A KL Lens on Quantization: Fast, Forward-Only Sensitivity for Mixed-Precision SSM-Transformer Models","created":"2026-04-15","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":"2509.00141","title":"Scaling Legal AI: Benchmarking Mamba and Transformers for Statutory Classification and Case Law Retrieval","created":"2025-08-29","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":"2511.10480","title":"Scalable Synthesis of distributed LLM workloads through Symbolic Tensor Graphs","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2602.03922","title":"Online Vector Quantized Attention","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2603.02874","title":"Retrievit: In-context Retrieval Capabilities of Transformers, State Space Models, and Hybrid Architectures","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2603.15954","title":"MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment","created":"2026-03-16","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":"2606.12364","title":"On Subquadratic Architectures: From Applications to Principles","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2608.21199","title":"Tydra: An Efficient Hybrid Model for Tabular Data","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2608.29539","title":"LoGo: Token-Level Dynamic Local-Global Attention","created":"2026-08-30","cited_by_count":1,"area":null},{"id":"2507.22250","title":"Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2603.09037","title":"WS-Net: Weak-Signal Representation Learning and Gated Abundance Reconstruction for Hyperspectral Unmixing via State-Space and Weak Signal Attention Fusion","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2604.06129","title":"PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.22127","title":"Where Should LoRA Go? Component-Type Placement in Hybrid Language Models","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2604.22442","title":"HubRouter: A Pluggable Sub-Quadratic Routing Primitive for Hybrid Sequence Models","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2604.24715","title":"Long-Context Aware Upcycling: A New Frontier for Hybrid LLM Scaling","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.24330","title":"Interdomain Attention: Beyond Token-Level Key-Value Memory","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.02332","title":"Forget Attention: Importance-Aware Attention Is All You Need","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.10244","title":"DSSMs: State Space Models with Explicit Memory via Delay Differential Equations","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2609.39661","title":"The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}