{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"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":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"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":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"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":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"id":"1606.06031","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","created":"2016-06-20","cited_by_count":992},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2404.14469","title":"SnapKV: LLM Knows What You are Looking for Before Generation","created":"2024-04-22","cited_by_count":880},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"1912.00582","title":"BLiMP: The Benchmark of Linguistic Minimal Pairs for English","created":"2019-12-02","cited_by_count":564},{"id":"2412.06464","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","created":"2024-12-09","cited_by_count":532},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502},{"id":"2003.05997","title":"Efficient Content-Based Sparse Attention with Routing Transformers","created":"2020-03-12","cited_by_count":471},{"id":"2305.17118","title":"Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time","created":"2023-05-26","cited_by_count":439},{"id":"2406.02069","title":"PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling","created":"2024-06-04","cited_by_count":432},{"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":"2202.08906","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","created":"2022-02-17","cited_by_count":399},{"id":"2103.16716","title":"BASE Layers: Simplifying Training of Large, Sparse Models","created":"2021-03-30","cited_by_count":320},{"id":"2404.02258","title":"Mixture-of-Depths: Dynamically allocating compute in transformer-based language models","created":"2024-04-02","cited_by_count":258},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237},{"id":"2402.01032","title":"Repeat After Me: Transformers are Better than State Space Models at Copying","created":"2024-02-01","cited_by_count":216},{"id":"2005.00743","title":"Synthesizer: Rethinking Self-Attention in Transformer Models","created":"2020-05-02","cited_by_count":205},{"id":"2312.04927","title":"Zoology: Measuring and Improving Recall in Efficient Language Models","created":"2023-12-08","cited_by_count":204},{"id":"2007.04825","title":"Fast Transformers with Clustered Attention","created":"2020-07-09","cited_by_count":123},{"id":"2402.04248","title":"Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks","created":"2024-02-06","cited_by_count":105},{"id":"2210.10340","title":"The Devil in Linear Transformer","created":"2022-10-19","cited_by_count":98},{"id":"2305.14705","title":"Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models","created":"2023-05-24","cited_by_count":65},{"id":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59},{"id":"2404.07413","title":"JetMoE: Reaching Llama2 Performance with 0.1M Dollars","created":"2024-04-11","cited_by_count":57},{"id":"2412.12094","title":"SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator","created":"2024-12-16","cited_by_count":41},{"id":"2212.08136","title":"Efficient Long Sequence Modeling via State Space Augmented Transformer","created":"2022-12-15","cited_by_count":37},{"id":"2310.10837","title":"Approximating Two-Layer Feedforward Networks for Efficient Transformers","created":"2023-10-16","cited_by_count":27},{"id":"2412.14468","title":"HashAttention: Semantic Sparsity for Faster Inference","created":"2024-12-19","cited_by_count":24},{"id":"2504.06214","title":"From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models","created":"2025-04-08","cited_by_count":14},{"id":"2310.12442","title":"Efficient Long-Range Transformers: You Need to Attend More, but Not Necessarily at Every Layer","created":"2023-10-19","cited_by_count":13}],"next_cursor":null}