{"total":177,"rows":[{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120,"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":"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":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146,"area":null},{"id":"2405.05254","title":"You Only Cache Once: Decoder-Decoder Architectures for Language Models","created":"2024-05-08","cited_by_count":144,"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":"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":"2409.05746","title":"LLMs Will Always Hallucinate, and We Need to Live With This","created":"2024-09-09","cited_by_count":78,"area":null},{"id":"2410.18745","title":"Why Does the Effective Context Length of LLMs Fall Short?","created":"2024-10-24","cited_by_count":63,"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":"2404.09937","title":"Compression Represents Intelligence Linearly","created":"2024-04-15","cited_by_count":56,"area":null},{"id":"2502.01563","title":"Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding","created":"2025-02-03","cited_by_count":47,"area":null},{"id":"2405.05417","title":"Fishing for Magikarp: Automatically Detecting Under-trained Tokens in Large Language Models","created":"2024-05-08","cited_by_count":46,"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":"2410.12360","title":"Towards Neural Scaling Laws for Time Series Foundation Models","created":"2024-10-16","cited_by_count":33,"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":"2411.00136","title":"LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators","created":"2024-10-31","cited_by_count":32,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"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":"2501.05414","title":"LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation","created":"2025-01-09","cited_by_count":29,"area":null},{"id":"2502.03738","title":"Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More","created":"2025-02-06","cited_by_count":28,"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":"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":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"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":"2507.19595","title":"Efficient Attention Mechanisms for Large Language Models: A Survey","created":"2025-07-25","cited_by_count":22,"area":null},{"id":"2405.06067","title":"HMT: Hierarchical Memory Transformer for Efficient Long Context Language Processing","created":"2024-05-09","cited_by_count":21,"area":null},{"id":"2412.14166","title":"MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data","created":"2024-12-18","cited_by_count":21,"area":null},{"id":"2406.16330","title":"Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging","created":"2024-06-24","cited_by_count":19,"area":null},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2505.08137","title":"Large Language Models for Computer-Aided Design: A Survey","created":"2025-05-13","cited_by_count":18,"area":null},{"id":"2507.18074","title":"Neural Architecture Discovery via Autonomous Evolution","created":"2025-07-24","cited_by_count":16,"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":"2406.12295","title":"Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding","created":"2024-06-18","cited_by_count":13,"area":null},{"id":"2410.04727","title":"Forgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-context Models","created":"2024-10-07","cited_by_count":13,"area":null},{"id":"2410.08703","title":"On the token distance modeling ability of higher RoPE attention dimension","created":"2024-10-11","cited_by_count":13,"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":"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":"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":"2510.07318","title":"Artificial Hippocampus Networks for Efficient Long-Context Modeling","created":"2025-10-08","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":"2410.04798","title":"DAPE V2: Process Attention Score as Feature Map for Length Extrapolation","created":"2024-10-07","cited_by_count":10,"area":null},{"id":"2502.16684","title":"WildLong: Synthesizing Realistic Long-Context Instruction Data at Scale","created":"2025-02-23","cited_by_count":9,"area":null},{"id":"2506.05320","title":"Generalizable, real-time neural decoding with hybrid state-space models","created":"2025-06-05","cited_by_count":9,"area":null},{"id":"2404.02882","title":"Linear Attention Sequence Parallelism","created":"2024-04-03","cited_by_count":8,"area":null},{"id":"2407.08642","title":"Towards Building Specialized Generalist AI with System 1 and System 2 Fusion","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2505.16811","title":"Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2603.14360","title":"M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling","created":"2026-03-15","cited_by_count":8,"area":null},{"id":"2406.09833","title":"SHMamba: Structured Hyperbolic State Space Model for Audio-Visual Question Answering","created":"2024-06-14","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":"2411.17207","title":"On the Efficiency of NLP-Inspired Methods for Tabular Deep Learning","created":"2024-11-26","cited_by_count":7,"area":null},{"id":"2411.17800","title":"STAR: Synthesis of Tailored Architectures","created":"2024-11-26","cited_by_count":7,"area":null},{"id":"2412.18177","title":"Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization","created":"2024-12-24","cited_by_count":7,"area":null},{"id":"2501.16085","title":"ARFlow: Autoregressive Flow with Hybrid Linear Attention","created":"2025-01-27","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":"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":"2506.02921","title":"A Controllable Examination for Long-Context Language Models","created":"2025-06-03","cited_by_count":7,"area":null},{"id":"2510.00379","title":"Composer: A Search Framework for Hybrid Neural Architecture Design","created":"2025-10-01","cited_by_count":7,"area":null},{"id":"2510.24606","title":"Long-Context Modeling with Dynamic Hierarchical Sparse Attention for Memory-Constrained LLM Inference","created":"2025-10-28","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":"2511.13912","title":"Compute-in-Memory Implementation of State Space Models for Event Sequence Processing","created":"2025-11-17","cited_by_count":6,"area":null},{"id":"2605.26797","title":"Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior","created":"2026-05-26","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","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":"2409.18828","title":"MECG-E: Mamba-based ECG Enhancer for Baseline Wander Removal","created":"2024-09-27","cited_by_count":5,"area":null},{"id":"2501.16368","title":"Foundation Models for CPS-IoT: Opportunities and Challenges","created":"2025-01-22","cited_by_count":5,"area":null},{"id":"2503.02354","title":"CoServe: Efficient Collaboration-of-Experts (CoE) Model Inference with Limited Memory","created":"2025-03-04","cited_by_count":5,"area":null},{"id":"2505.17083","title":"Scale-invariant Attention","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2506.07919","title":"Uncovering the Computational Roles of Nonlinearity in Sequence Modeling Using Almost-Linear RNNs","created":"2025-06-09","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":"2512.22208","title":"Open-Source Multimodal Moxin Models with Moxin-VLM and Moxin-VLA","created":"2025-12-22","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":"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":"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":"2502.17605","title":"PICASO: Permutation-Invariant Context Composition with State Space Models","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2507.01652","title":"Autoregressive Image Generation with Linear Complexity: A Spatial-Aware Decay Perspective","created":"2025-07-02","cited_by_count":4,"area":null},{"id":"2602.18283","title":"HyTRec: A Hybrid Temporal-Aware Attention Architecture for Long Behavior Sequential Recommendation","created":"2026-02-20","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":"2605.05838","title":"MDN: Parallelizing Stepwise Momentum for Delta Linear Attention","created":"2026-05-07","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":"2607.25380","title":"Memory for Large Language Models","created":"2026-07-28","cited_by_count":4,"area":null},{"id":"2409.11887","title":"DocMamba: Efficient Document Pre-training with State Space Model","created":"2024-09-18","cited_by_count":3,"area":null},{"id":"2502.01673","title":"Multilingual State Space Models for Structured Question Answering in Indic Languages","created":"2025-02-01","cited_by_count":3,"area":null},{"id":"2502.12085","title":"APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2502.18277","title":"Self-Adjust Softmax","created":"2025-02-25","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":"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":"2507.04239","title":"Scaling Context Requires Rethinking Attention","created":"2025-07-06","cited_by_count":3,"area":null},{"id":"2510.02228","title":"xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity","created":"2025-10-02","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":"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":"2608.02870","title":"Maglev: Sliding Recurrent Memory","created":"2026-08-03","cited_by_count":3,"area":null}],"next_cursor":"100"}