{"list":"other","total":73,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"2405.04434","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","created":"2024-05-07","cited_by_count":1135},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"id":"1907.00235","title":"Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting","created":"2019-06-29","cited_by_count":607},{"id":"2412.06464","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","created":"2024-12-09","cited_by_count":532},{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502},{"id":"2406.10774","title":"Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference","created":"2024-06-16","cited_by_count":501},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2003.05997","title":"Efficient Content-Based Sparse Attention with Routing Transformers","created":"2020-03-12","cited_by_count":471},{"id":"2502.11089","title":"Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention","created":"2025-02-16","cited_by_count":407},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401},{"id":"2406.06484","title":"Parallelizing Linear Transformers with the Delta Rule over Sequence Length","created":"2024-06-10","cited_by_count":396},{"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},{"id":"2407.04620","title":"Learning to (Learn at Test Time): RNNs with Expressive Hidden States","created":"2024-07-05","cited_by_count":355},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328},{"id":"2405.04517","title":"xLSTM: Extended Long Short-Term Memory","created":"2024-05-07","cited_by_count":327},{"id":"1908.11775","title":"Transformer Dissection: A Unified Understanding of Transformer's Attention via the Lens of Kernel","created":"2019-08-30","cited_by_count":213},{"id":"2202.08791","title":"cosFormer: Rethinking Softmax in Attention","created":"2022-02-17","cited_by_count":213},{"id":"2305.16300","title":"Landmark Attention: Random-Access Infinite Context Length for Transformers","created":"2023-05-25","cited_by_count":213},{"id":"2307.02486","title":"LongNet: Scaling Transformers to 1,000,000,000 Tokens","created":"2023-07-05","cited_by_count":204},{"id":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198},{"id":"2202.10447","title":"Transformer Quality in Linear Time","created":"2022-02-21","cited_by_count":191},{"id":"2501.08313","title":"MiniMax-01: Scaling Foundation Models with Lightning Attention","created":"2025-01-14","cited_by_count":166},{"id":"2404.05892","title":"Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence","created":"2024-04-08","cited_by_count":159},{"id":"2405.05254","title":"You Only Cache Once: Decoder-Decoder Architectures for Language Models","created":"2024-05-08","cited_by_count":144},{"id":"2503.14456","title":"RWKV-7 \"Goose\" with Expressive Dynamic State Evolution","created":"2025-03-18","cited_by_count":141},{"id":"2503.16428","title":"XAttention: Block Sparse Attention with Antidiagonal Scoring","created":"2025-03-20","cited_by_count":137},{"id":"2404.07904","title":"HGRN2: Gated Linear RNNs with State Expansion","created":"2024-04-11","cited_by_count":127},{"id":"2410.13276","title":"SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs","created":"2024-10-17","cited_by_count":124},{"id":"2502.20766","title":"FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference","created":"2025-02-28","cited_by_count":123},{"id":"2402.04347","title":"The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry","created":"2024-02-06","cited_by_count":120},{"id":"2409.10516","title":"RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval","created":"2024-09-16","cited_by_count":116},{"id":"2105.14103","title":"An Attention Free Transformer","created":"2021-05-28","cited_by_count":112},{"id":"2410.16179","title":"MagicPIG: LSH Sampling for Efficient LLM Generation","created":"2024-10-21","cited_by_count":111},{"id":"2311.04823","title":"Hierarchically Gated Recurrent Neural Network for Sequence Modeling","created":"2023-11-08","cited_by_count":102},{"id":"2106.01540","title":"Luna: Linear Unified Nested Attention","created":"2021-06-03","cited_by_count":96},{"id":"2409.07146","title":"Gated Slot Attention for Efficient Linear-Time Sequence Modeling","created":"2024-09-11","cited_by_count":76},{"id":"2505.23735","title":"ATLAS: Learning to Optimally Memorize the Context at Test Time","created":"2025-05-29","cited_by_count":66},{"id":"2412.03213","title":"ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression","created":"2024-12-04","cited_by_count":65},{"id":"2407.14207","title":"Longhorn: State Space Models are Amortized Online Learners","created":"2024-07-19","cited_by_count":59},{"id":"2506.07900","title":"MiniCPM4: Ultra-Efficient LLMs on End Devices","created":"2025-06-09","cited_by_count":52},{"id":"2501.18795","title":"Rope to Nope and Back Again: A New Hybrid Attention Strategy","created":"2025-01-30","cited_by_count":47},{"id":"2311.01927","title":"GateLoop: Fully Data-Controlled Linear Recurrence for Sequence Modeling","created":"2023-11-03","cited_by_count":46},{"id":"2410.05355","title":"Falcon Mamba: The First Competitive Attention-free 7B Language Model","created":"2024-10-07","cited_by_count":46},{"id":"2408.07092","title":"Post-Training Sparse Attention with Double Sparsity","created":"2024-08-11","cited_by_count":45},{"id":"2110.02488","title":"ABC: Attention with Bounded-memory Control","created":"2021-10-06","cited_by_count":36},{"id":"2307.14995","title":"TransNormerLLM: A Faster and Better Large Language Model with Improved TransNormer","created":"2023-07-27","cited_by_count":34},{"id":"2405.17381","title":"Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention","created":"2024-05-27","cited_by_count":31},{"id":"2506.08889","title":"SeerAttention-R: Sparse Attention Adaptation for Long Reasoning","created":"2025-06-10","cited_by_count":30},{"id":"2507.06607","title":"Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation","created":"2025-07-09","cited_by_count":11},{"id":"2506.04108","title":"Rectified Sparse Attention","created":"2025-06-04","cited_by_count":10}],"next_cursor":null}