{"total":96,"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":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146,"area":null},{"id":"2509.26645","title":"TTT3R: 3D Reconstruction as Test-Time Training","created":"2025-09-30","cited_by_count":129,"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":"2411.13676","title":"Hymba: A Hybrid-head Architecture for Small Language Models","created":"2024-11-20","cited_by_count":99,"area":null},{"id":"2409.07146","title":"Gated Slot Attention for Efficient Linear-Time Sequence Modeling","created":"2024-09-11","cited_by_count":76,"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":"2512.20856","title":"NVIDIA Nemotron 3: Efficient and Open Intelligence","created":"2025-12-24","cited_by_count":65,"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":"2502.12671","title":"Baichuan-M1: Pushing the Medical Capability of Large Language Models","created":"2025-02-18","cited_by_count":43,"area":null},{"id":"2508.15884","title":"Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search","created":"2025-08-21","cited_by_count":41,"area":null},{"id":"2507.06457","title":"A Systematic Analysis of Hybrid Linear Attention","created":"2025-07-08","cited_by_count":39,"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":"2507.02782","title":"Understanding and Improving Length Generalization in Recurrent Models","created":"2025-07-03","cited_by_count":23,"area":null},{"id":"2502.07272","title":"GENERator: A Long-Context Generative Genomic Foundation Model","created":"2025-02-11","cited_by_count":22,"area":null},{"id":"2604.03444","title":"Olmo Hybrid: From Theory to Practice and Back","created":"2026-04-03","cited_by_count":22,"area":null},{"id":"2411.15242","title":"The Zamba2 Suite: Technical Report","created":"2024-11-22","cited_by_count":21,"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":"2509.22284","title":"Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models","created":"2025-09-26","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":"2511.18890","title":"Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models","created":"2025-11-24","cited_by_count":15,"area":null},{"id":"2408.04713","title":"DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models","created":"2024-08-08","cited_by_count":14,"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":"2507.16577","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":"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":"2602.20160","title":"tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction","created":"2026-02-23","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":"2411.19455","title":"Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models","created":"2024-11-29","cited_by_count":9,"area":null},{"id":"2504.16795","title":"Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access","created":"2025-04-23","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":"2411.19574","title":"KV Shifting Attention Enhances Language Modeling","created":"2024-11-29","cited_by_count":8,"area":null},{"id":"2508.19029","title":"Revisiting associative recall in modern recurrent models","created":"2025-08-26","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":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7,"area":null},{"id":"2409.10489","title":"Flash STU: Fast Spectral Transform Units","created":"2024-09-16","cited_by_count":7,"area":null},{"id":"2410.06718","title":"MatMamba: A Matryoshka State Space Model","created":"2024-10-09","cited_by_count":7,"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":"2410.06577","title":"Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2504.03101","title":"Single-Pass Document Scanning for Question Answering","created":"2025-04-04","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":"2607.25357","title":"Raven: High-Recall Sequence Modeling with Sparse Memory Routing","created":"2026-07-28","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":"2507.00449","title":"Overcoming Long-Context Limitations of State-Space Models via Context-Dependent Sparse Attention","created":"2025-07-01","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":"2605.08301","title":"Priming: Hybrid State Space Models From Pre-trained Transformers","created":"2026-05-08","cited_by_count":5,"area":null},{"id":"2408.07802","title":"Kraken: Inherently Parallel Transformers For Efficient Multi-Device Inference","created":"2024-08-14","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":"2510.14826","title":"To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models","created":"2025-10-16","cited_by_count":4,"area":null},{"id":"2603.08859","title":"Expressivity-Efficiency Tradeoffs for Hybrid Sequence Models","created":"2026-03-09","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":"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":"2506.09507","title":"TransXSSM: A Hybrid Transformer State Space Model with Unified Rotary Position Embedding","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2510.13245","title":"CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation","created":"2025-10-15","cited_by_count":3,"area":null},{"id":"2510.19861","title":"Some Attention is All You Need for Retrieval","created":"2025-10-21","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":"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":"2603.15653","title":"Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context","created":"2026-03-07","cited_by_count":2,"area":null},{"id":"2411.17283","title":"BadScan: An Architectural Backdoor Attack on Visual State Space Models","created":"2024-11-26","cited_by_count":1,"area":null},{"id":"2505.24033","title":"Studying the Soupability of Documents in State Space Models","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2507.12442","title":"Characterizing State Space Model and Hybrid Language Model Performance with Long Context","created":"2025-07-16","cited_by_count":1,"area":null},{"id":"2507.19353","title":"Smooth Reading: Bridging the Gap of Recurrent LLM to Self-Attention LLM on Long-Context Tasks","created":"2025-07-25","cited_by_count":1,"area":null},{"id":"2509.05550","title":"TreeGPT: Pure TreeFFN Encoder-Decoder Architecture for Structured Reasoning Without Attention Mechanisms","created":"2025-09-06","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":"2511.00576","title":"FlashEVA: Accelerating LLM inference via Efficient Attention","created":"2025-11-01","cited_by_count":1,"area":null},{"id":"2605.08587","title":"Kaczmarz Linear Attention","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.21070","title":"Towards Understanding Self-Pretraining for Sequence Classification","created":"2026-05-20","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":"2606.20936","title":"Comparing Transformers and Hybrid Models at the Token Level","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2609.12814","title":"RunningTensor: Generalizing Linear Attention to Higher-Order Recurrent States","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2409.06724","title":"MLP, XGBoost, KAN, TDNN, and LSTM-GRU Hybrid RNN with Attention for SPX and NDX European Call Option Pricing","created":"2024-08-26","cited_by_count":0,"area":null},{"id":"2409.07609","title":"Survival of the Cheapest: Cost-Aware Hardware Adaptation for Adversarial Robustness","created":"2024-09-11","cited_by_count":0,"area":null},{"id":"2501.00692","title":"Adjoint sharding for very long context training of state space models","created":"2025-01-01","cited_by_count":0,"area":null},{"id":"2504.06704","title":"CAT: Circular-Convolutional Attention for Sub-Quadratic Transformers","created":"2025-04-09","cited_by_count":0,"area":null},{"id":"2511.16839","title":"Trajectory-guided discharge stratification for heart failure using short-context electronic health record sequence modeling","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2601.21307","title":"Mam-App: A Novel Parameter-Efficient Mamba Model for Apple Leaf Disease Classification","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.00862","title":"Towards Multiscale Graph-based Protein Learning with Geometric Secondary Structural Motifs","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.12021","title":"Improved state mixing in higher-order and block diagonal linear recurrent networks","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2604.01652","title":"ThinknCheck: Grounded Claim Verification with Compact, Reasoning-Driven, and Interpretable Models","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.24013","title":"CommFuse: Hiding Tail Latency via Communication Decomposition and Fusion for Distributed LLM Training","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.06683","title":"Toeplitz MLP Mixers are Low Complexity, Information-Rich Sequence Models","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.19150","title":"Flash PD-SSM: Memory-Optimized Structured Sparse State-Space Models","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.31367","title":"Trading Complexity for Expressivity Through Structured Generalized Linear Token Mixing","created":"2026-05-29","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":"2608.01034","title":"Opt.Gear Technical Report","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2609.16540","title":"On the Importance of Gating: Memorization vs. In-Context Learning in State Space Models","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.25802","title":"Latest Exact Match Attention","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.32942","title":"The Key Handoff: Retrieval in Hybrid Language Models","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.00398","title":"WIPSNet: Deep Learning for Paediatric Wheeze Detection from Overnight Impedance Pneumography","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01172","title":"Learning Rate Transfer for Hybrid Transformer-SSM Architectures","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.04518","title":"Length Generalization Needs Proper Regularization","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}