{"total":2022,"rows":[{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703,"area":null},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673,"area":null},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598,"area":null},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465,"area":"ssm"},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104,"area":null},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984,"area":null},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969,"area":null},{"id":"2306.14048","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","created":"2023-06-24","cited_by_count":832,"area":"inference"},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827,"area":null},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788,"area":"ssm"},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681,"area":"diffusion"},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613,"area":null},{"id":"2306.13643","title":"LightGlue: Local Feature Matching at Light Speed","created":"2023-06-23","cited_by_count":590,"area":null},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569,"area":null},{"id":"2412.06464","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","created":"2024-12-09","cited_by_count":532,"area":null},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527,"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":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514,"area":"ssm"},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499,"area":null},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471,"area":null},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419,"area":null},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"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":"2112.07658","title":"AdaViT: Adaptive Tokens for Efficient Vision Transformer","created":"2021-12-14","cited_by_count":362,"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":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354,"area":null},{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350,"area":"ssm"},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347,"area":null},{"id":"2104.02112","title":"Efficient Attentions for Long Document Summarization","created":"2021-04-05","cited_by_count":345,"area":null},{"id":"2105.14995","title":"Choose a Transformer: Fourier or Galerkin","created":"2021-05-31","cited_by_count":343,"area":null},{"id":"2410.10629","title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","created":"2024-10-14","cited_by_count":340,"area":"diffusion"},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338,"area":null},{"id":"2302.14376","title":"GNOT: A General Neural Operator Transformer for Operator Learning","created":"2023-02-28","cited_by_count":336,"area":null},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328,"area":"lr"},{"id":"2402.02366","title":"Transolver: A Fast Transformer Solver for PDEs on General Geometries","created":"2024-02-04","cited_by_count":326,"area":null},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305,"area":null},{"id":"2309.16039","title":"Effective Long-Context Scaling of Foundation Models","created":"2023-09-27","cited_by_count":303,"area":null},{"id":"2209.15425","title":"Spikformer: When Spiking Neural Network Meets Transformer","created":"2022-09-29","cited_by_count":271,"area":null},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265,"area":null},{"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":"2103.04922","title":"Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models","created":"2021-03-08","cited_by_count":252,"area":null},{"id":"2111.13587","title":"Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers","created":"2021-11-24","cited_by_count":248,"area":null},{"id":"2507.02259","title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","created":"2025-07-03","cited_by_count":246,"area":"lr"},{"id":"2201.09873","title":"Transformers in Medical Imaging: A Survey","created":"2022-01-24","cited_by_count":245,"area":null},{"id":"2402.19427","title":"Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models","created":"2024-02-29","cited_by_count":242,"area":null},{"id":"2402.14905","title":"MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases","created":"2024-02-22","cited_by_count":223,"area":null},{"id":"2303.11797","title":"CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation","created":"2023-03-21","cited_by_count":219,"area":null},{"id":"2502.01776","title":"Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity","created":"2025-02-03","cited_by_count":217,"area":"diffusion"},{"id":"2402.01032","title":"Repeat After Me: Transformers are Better than State Space Models at Copying","created":"2024-02-01","cited_by_count":216,"area":null},{"id":"2202.08791","title":"cosFormer: Rethinking Softmax in Attention","created":"2022-02-17","cited_by_count":213,"area":"lr"},{"id":"2410.10781","title":"When Attention Sink Emerges in Language Models: An Empirical View","created":"2024-10-14","cited_by_count":208,"area":"inference"},{"id":"2103.15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","created":"2021-03-29","cited_by_count":207,"area":null},{"id":"2106.09553","title":"Large-Scale Chemical Language Representations Capture Molecular Structure and Properties","created":"2021-06-17","cited_by_count":206,"area":null},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2307.02486","title":"LongNet: Scaling Transformers to 1,000,000,000 Tokens","created":"2023-07-05","cited_by_count":204,"area":null},{"id":"2110.03675","title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis","created":"2021-10-07","cited_by_count":200,"area":null},{"id":"2404.07143","title":"Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention","created":"2024-04-10","cited_by_count":200,"area":null},{"id":"2310.16028","title":"What Algorithms can Transformers Learn? A Study in Length Generalization","created":"2023-10-24","cited_by_count":199,"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":"2402.04617","title":"InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory","created":"2024-02-07","cited_by_count":197,"area":"agents"},{"id":"2510.26692","title":"Kimi Linear: An Expressive, Efficient Attention Architecture","created":"2025-10-30","cited_by_count":196,"area":"deeprl"},{"id":"2202.10447","title":"Transformer Quality in Linear Time","created":"2022-02-21","cited_by_count":191,"area":null},{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188,"area":null},{"id":"2402.17152","title":"Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations","created":"2024-02-27","cited_by_count":188,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183,"area":null},{"id":"2503.02175","title":"DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models","created":"2025-03-04","cited_by_count":181,"area":"mllm"},{"id":"2101.07448","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","created":"2021-01-19","cited_by_count":176,"area":null},{"id":"2208.14201","title":"ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer","created":"2022-08-30","cited_by_count":171,"area":null},{"id":"2308.00442","title":"FLatten Transformer: Vision Transformer using Focused Linear Attention","created":"2023-08-01","cited_by_count":171,"area":null},{"id":"2305.07185","title":"MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers","created":"2023-05-12","cited_by_count":170,"area":null},{"id":"2410.02367","title":"SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration","created":"2024-10-03","cited_by_count":160,"area":"inference"},{"id":"2404.05892","title":"Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence","created":"2024-04-08","cited_by_count":159,"area":null},{"id":"2205.12257","title":"OnePose: One-Shot Object Pose Estimation without CAD Models","created":"2022-05-24","cited_by_count":157,"area":null},{"id":"2202.13903","title":"Bayesian Structure Learning with Generative Flow Networks","created":"2022-02-28","cited_by_count":153,"area":null},{"id":"2510.11967","title":"Scaling Long-Horizon LLM Agent via Context-Folding","created":"2025-10-13","cited_by_count":148,"area":"agents"},{"id":"2307.01694","title":"Spike-driven Transformer","created":"2023-07-04","cited_by_count":146,"area":null},{"id":"2303.00748","title":"Efficient and Explicit Modelling of Image Hierarchies for Image Restoration","created":"2023-03-01","cited_by_count":145,"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":"2405.07992","title":"MambaOut: Do We Really Need Mamba for Vision?","created":"2024-05-13","cited_by_count":143,"area":"ssm"},{"id":"2504.12626","title":"Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models","created":"2025-04-17","cited_by_count":143,"area":"diffusion"},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141,"area":null},{"id":"2107.00910","title":"Learned Token Pruning for Transformers","created":"2021-07-02","cited_by_count":139,"area":"inference"},{"id":"2209.04881","title":"On The Computational Complexity of Self-Attention","created":"2022-09-11","cited_by_count":139,"area":null},{"id":"2607.24653","title":"Kimi K3: Open Frontier Intelligence","created":"2026-07-27","cited_by_count":138,"area":"agents"},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136,"area":null},{"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":"2405.12981","title":"Reducing Transformer Key-Value Cache Size with Cross-Layer Attention","created":"2024-05-21","cited_by_count":131,"area":"inference"},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2110.15343","title":"Scatterbrain: Unifying Sparse and Low-rank Attention Approximation","created":"2021-10-28","cited_by_count":130,"area":null},{"id":"2201.02767","title":"QuadTree Attention for Vision Transformers","created":"2022-01-08","cited_by_count":129,"area":null},{"id":"2509.26645","title":"TTT3R: 3D Reconstruction as Test-Time Training","created":"2025-09-30","cited_by_count":129,"area":null},{"id":"2110.11945","title":"SOFT: Softmax-free Transformer with Linear Complexity","created":"2021-10-22","cited_by_count":128,"area":null},{"id":"2305.01625","title":"Unlimiformer: Long-Range Transformers with Unlimited Length Input","created":"2023-05-02","cited_by_count":128,"area":null},{"id":"2305.17560","title":"Scalable Transformer for PDE Surrogate Modeling","created":"2023-05-27","cited_by_count":128,"area":null},{"id":"2212.10554","title":"A Length-Extrapolatable Transformer","created":"2022-12-20","cited_by_count":127,"area":null},{"id":"2404.07904","title":"HGRN2: Gated Linear RNNs with State Expansion","created":"2024-04-11","cited_by_count":127,"area":null},{"id":"2403.09054","title":"Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference","created":"2024-03-14","cited_by_count":126,"area":"inference"}],"next_cursor":"100"}