{"total":1336,"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":"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":"2407.04620","title":"Learning to (Learn at Test Time): RNNs with Expressive Hidden States","created":"2024-07-05","cited_by_count":355,"area":"ssm"},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328,"area":"lr"},{"id":"2505.06708","title":"Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free","created":"2025-05-10","cited_by_count":283,"area":"moe"},{"id":"2506.13585","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","created":"2025-06-16","cited_by_count":263,"area":"lr"},{"id":"2502.10517","title":"KernelBench: Can LLMs Write Efficient GPU Kernels?","created":"2025-02-14","cited_by_count":225,"area":null},{"id":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198,"area":"moe"},{"id":"2510.26692","title":"Kimi Linear: An Expressive, Efficient Attention Architecture","created":"2025-10-30","cited_by_count":196,"area":"deeprl"},{"id":"2406.07887","title":"An Empirical Study of Mamba-based Language Models","created":"2024-06-12","cited_by_count":186,"area":"ssm"},{"id":"2506.21734","title":"Hierarchical Reasoning Model","created":"2025-06-26","cited_by_count":177,"area":"lr"},{"id":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146,"area":null},{"id":"2607.24653","title":"Kimi K3: Open Frontier Intelligence","created":"2026-07-27","cited_by_count":138,"area":"agents"},{"id":"2503.21614","title":"A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond","created":"2025-03-27","cited_by_count":132,"area":"lr"},{"id":"2505.23884","title":"Test-Time Training Done Right","created":"2025-05-29","cited_by_count":130,"area":"diffusion"},{"id":"2509.26645","title":"TTT3R: 3D Reconstruction as Test-Time Training","created":"2025-09-30","cited_by_count":129,"area":null},{"id":"2410.02694","title":"HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly","created":"2024-10-03","cited_by_count":125,"area":null},{"id":"2408.15237","title":"The Mamba in the Llama: Distilling and Accelerating Hybrid Models","created":"2024-08-27","cited_by_count":122,"area":"ssm"},{"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":"2508.14444","title":"NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model","created":"2025-08-20","cited_by_count":108,"area":"lr"},{"id":"2505.18875","title":"Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation","created":"2025-05-24","cited_by_count":106,"area":"diffusion"},{"id":"2512.20848","title":"Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2025-12-23","cited_by_count":104,"area":"lr"},{"id":"2409.02889","title":"LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture","created":"2024-09-04","cited_by_count":102,"area":"mllm"},{"id":"2411.12537","title":"Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues","created":"2024-11-19","cited_by_count":101,"area":"ssm"},{"id":"2504.05298","title":"One-Minute Video Generation with Test-Time Training","created":"2025-04-07","cited_by_count":101,"area":"ssm"},{"id":"2504.03624","title":"Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models","created":"2025-04-04","cited_by_count":100,"area":"lr"},{"id":"2411.13676","title":"Hymba: A Hybrid-head Architecture for Small Language Models","created":"2024-11-20","cited_by_count":99,"area":null},{"id":"2410.12261","title":"CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching","created":"2024-10-16","cited_by_count":94,"area":null},{"id":"2603.15569","title":"Mamba-3: Improved Sequence Modeling using State Space Principles","created":"2026-03-16","cited_by_count":89,"area":"lr"},{"id":"2411.17697","title":"StableAnimator: High-Quality Identity-Preserving Human Image Animation","created":"2024-11-26","cited_by_count":88,"area":"diffusion"},{"id":"2408.03601","title":"DRAMA: An Efficient End-to-end Motion Planner for Autonomous Driving with Mamba","created":"2024-08-07","cited_by_count":87,"area":"driving"},{"id":"2507.06203","title":"A Survey on Latent Reasoning","created":"2025-07-08","cited_by_count":81,"area":"lr"},{"id":"2409.07146","title":"Gated Slot Attention for Efficient Linear-Time Sequence Modeling","created":"2024-09-11","cited_by_count":76,"area":null},{"id":"2502.10297","title":"DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products","created":"2025-02-14","cited_by_count":75,"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":"2507.07955","title":"Dynamic Chunking for End-to-End Hierarchical Sequence Modeling","created":"2025-07-10","cited_by_count":72,"area":null},{"id":"2410.01131","title":"nGPT: Normalized Transformer with Representation Learning on the Hypersphere","created":"2024-10-01","cited_by_count":70,"area":null},{"id":"2506.19852","title":"Radial Attention: $O(n\\log n)$ Sparse Attention with Energy Decay for Long Video Generation","created":"2025-06-24","cited_by_count":69,"area":"diffusion"},{"id":"2408.10189","title":"Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models","created":"2024-08-19","cited_by_count":67,"area":"ssm"},{"id":"2512.20856","title":"NVIDIA Nemotron 3: Efficient and Open Intelligence","created":"2025-12-24","cited_by_count":65,"area":null},{"id":"2603.15031","title":"Attention Residuals","created":"2026-03-16","cited_by_count":65,"area":null},{"id":"2504.13173","title":"It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization","created":"2025-04-17","cited_by_count":64,"area":null},{"id":"2505.20171","title":"Long-Context State-Space Video World Models","created":"2025-05-26","cited_by_count":64,"area":"wm"},{"id":"2512.23675","title":"End-to-End Test-Time Training for Long Context","created":"2025-12-29","cited_by_count":62,"area":null},{"id":"2412.10319","title":"SCBench: A KV Cache-Centric Analysis of Long-Context Methods","created":"2024-12-13","cited_by_count":60,"area":"inference"},{"id":"2604.12946","title":"Parcae: Scaling Laws For Stable Looped Language Models","created":"2026-04-14","cited_by_count":55,"area":null},{"id":"2605.15178","title":"SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer","created":"2026-05-14","cited_by_count":55,"area":"wm"},{"id":"2410.01949","title":"Discrete Copula Diffusion","created":"2024-10-02","cited_by_count":54,"area":"diffusion"},{"id":"2503.02130","title":"Forgetting Transformer: Softmax Attention with a Forget Gate","created":"2025-03-03","cited_by_count":53,"area":null},{"id":"2408.12570","title":"Jamba-1.5: Hybrid Transformer-Mamba Models at Scale","created":"2024-08-22","cited_by_count":50,"area":"ssm"},{"id":"2503.04130","title":"STORM: Token-Efficient Long Video Understanding for Multimodal LLMs","created":"2025-03-06","cited_by_count":49,"area":"mllm"},{"id":"2408.10920","title":"Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations","created":"2024-08-20","cited_by_count":47,"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":"2507.06952","title":"What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models","created":"2025-07-09","cited_by_count":47,"area":"wm"},{"id":"2410.05355","title":"Falcon Mamba: The First Competitive Attention-free 7B Language Model","created":"2024-10-07","cited_by_count":46,"area":"ssm"},{"id":"2412.20066","title":"MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration","created":"2024-12-28","cited_by_count":45,"area":"ssm"},{"id":"2407.09941","title":"Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers","created":"2024-07-13","cited_by_count":44,"area":"ssm"},{"id":"2409.02097","title":"LinFusion: 1 GPU, 1 Minute, 16K Image","created":"2024-09-03","cited_by_count":43,"area":"diffusion"},{"id":"2412.09856","title":"LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity","created":"2024-12-13","cited_by_count":43,"area":"diffusion"},{"id":"2407.01527","title":"KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches","created":"2024-07-01","cited_by_count":42,"area":"inference"},{"id":"2504.16053","title":"LongMamba: Enhancing Mamba's Long Context Capabilities via Training-Free Receptive Field Enlargement","created":"2025-04-22","cited_by_count":42,"area":"ssm"},{"id":"2410.15091","title":"Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion","created":"2024-10-19","cited_by_count":41,"area":"ssm"},{"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":"2509.19296","title":"Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation","created":"2025-09-23","cited_by_count":41,"area":"diffusion"},{"id":"2506.04761","title":"Log-Linear Attention","created":"2025-06-05","cited_by_count":40,"area":null},{"id":"2408.01129","title":"A Survey of Mamba","created":"2024-08-02","cited_by_count":39,"area":"ssm"},{"id":"2503.12030","title":"Hydra-NeXt: Robust Closed-Loop Driving with Open-Loop Training","created":"2025-03-15","cited_by_count":39,"area":"driving"},{"id":"2505.09343","title":"Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures","created":"2025-05-14","cited_by_count":39,"area":"moe"},{"id":"2507.06457","title":"A Systematic Analysis of Hybrid Linear Attention","created":"2025-07-08","cited_by_count":39,"area":null},{"id":"2510.14510","title":"Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective","created":"2025-10-16","cited_by_count":39,"area":null},{"id":"2410.04466","title":"Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective","created":"2024-10-06","cited_by_count":38,"area":"inference"},{"id":"2604.12374","title":"Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-04-14","cited_by_count":38,"area":"agents"},{"id":"2506.23858","title":"VMoBA: Mixture-of-Block Attention for Video Diffusion Models","created":"2025-06-30","cited_by_count":37,"area":"diffusion"},{"id":"2410.20399","title":"ThunderKittens: Simple, Fast, and Adorable AI Kernels","created":"2024-10-27","cited_by_count":36,"area":null},{"id":"2503.11579","title":"Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers","created":"2025-03-14","cited_by_count":36,"area":"mllm"},{"id":"2410.00379","title":"CXPMRG-Bench: Pre-training and Benchmarking for X-ray Medical Report Generation on CheXpert Plus Dataset","created":"2024-10-01","cited_by_count":35,"area":null},{"id":"2412.00678","title":"2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification","created":"2024-12-01","cited_by_count":35,"area":"ssm"},{"id":"2502.14458","title":"Llamba: Scaling Distilled Recurrent Models for Efficient Language Processing","created":"2025-02-20","cited_by_count":35,"area":"ssm"},{"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":"2512.17351","title":"Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers","created":"2025-12-19","cited_by_count":33,"area":null},{"id":"2605.22791","title":"Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention","created":"2026-05-21","cited_by_count":33,"area":"ssm"},{"id":"2406.07592","title":"MambaLRP: Explaining Selective State Space Sequence Models","created":"2024-06-11","cited_by_count":32,"area":"ssm"},{"id":"2409.02313","title":"On the Benefits of Memory for Modeling Time-Dependent PDEs","created":"2024-09-03","cited_by_count":31,"area":null},{"id":"2410.06672","title":"Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures","created":"2024-10-09","cited_by_count":31,"area":"ssm"},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","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":"2502.12170","title":"MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections","created":"2025-02-13","cited_by_count":31,"area":null},{"id":"2603.12201","title":"IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse","created":"2026-03-12","cited_by_count":31,"area":"agents"},{"id":"2604.08542","title":"Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction","created":"2026-04-09","cited_by_count":31,"area":null},{"id":"2506.08889","title":"SeerAttention-R: Sparse Attention Adaptation for Long Reasoning","created":"2025-06-10","cited_by_count":30,"area":"lr"},{"id":"2407.18559","title":"VSSD: Vision Mamba with Non-Causal State Space Duality","created":"2024-07-26","cited_by_count":29,"area":"ssm"},{"id":"2505.15431","title":"Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought","created":"2025-05-21","cited_by_count":29,"area":"lr"},{"id":"2409.03231","title":"State-space models are accurate and efficient neural operators for dynamical systems","created":"2024-09-05","cited_by_count":28,"area":"ssm"},{"id":"2410.04199","title":"LongGenBench: Long-context Generation Benchmark","created":"2024-10-05","cited_by_count":28,"area":null},{"id":"2412.16112","title":"CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up","created":"2024-12-20","cited_by_count":28,"area":"diffusion"},{"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}],"next_cursor":"100"}