{"list":"other","total":85,"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"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":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"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":"1606.06031","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","created":"2016-06-20","cited_by_count":992},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519},{"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":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328},{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327},{"id":"1906.06755","title":"Theoretical Limitations of Self-Attention in Neural Sequence Models","created":"2019-06-16","cited_by_count":288},{"id":"2402.12875","title":"Chain of Thought Empowers Transformers to Solve Inherently Serial Problems","created":"2024-02-20","cited_by_count":260},{"id":"2402.19427","title":"Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models","created":"2024-02-29","cited_by_count":242},{"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":"2402.18668","title":"Simple linear attention language models balance the recall-throughput tradeoff","created":"2024-02-28","cited_by_count":208},{"id":"2406.07522","title":"Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling","created":"2024-06-11","cited_by_count":174},{"id":"2501.08313","title":"MiniMax-01: Scaling Foundation Models with Lightning Attention","created":"2025-01-14","cited_by_count":166},{"id":"1909.00015","title":"Adaptively Sparse Transformers","created":"2019-08-30","cited_by_count":155},{"id":"2503.14456","title":"RWKV-7 \"Goose\" with Expressive Dynamic State Evolution","created":"2025-03-18","cited_by_count":141},{"id":"2306.02896","title":"Representational Strengths and Limitations of Transformers","created":"2023-06-05","cited_by_count":133},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131},{"id":"2404.07904","title":"HGRN2: Gated Linear RNNs with State Expansion","created":"2024-04-11","cited_by_count":127},{"id":"2311.00208","title":"What Formal Languages Can Transformers Express? A Survey","created":"2023-11-01","cited_by_count":124},{"id":"2402.04347","title":"The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry","created":"2024-02-06","cited_by_count":120},{"id":"2105.14103","title":"An Attention Free Transformer","created":"2021-05-28","cited_by_count":112},{"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":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102},{"id":"2407.18003","title":"Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption","created":"2024-07-25","cited_by_count":97},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72},{"id":"2210.02671","title":"A Logic for Expressing Log-Precision Transformers","created":"2022-10-06","cited_by_count":67},{"id":"2402.18510","title":"RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval","created":"2024-02-28","cited_by_count":64},{"id":"2404.07839","title":"RecurrentGemma: Moving Past Transformers for Efficient Open Language Models","created":"2024-04-11","cited_by_count":64},{"id":"2402.08164","title":"On Limitations of the Transformer Architecture","created":"2024-02-13","cited_by_count":63},{"id":"2407.05483","title":"Just read twice: closing the recall gap for recurrent language models","created":"2024-07-07","cited_by_count":60},{"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":"2503.03961","title":"A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers","created":"2025-03-05","cited_by_count":53},{"id":"2412.06590","title":"Bridging the Divide: Reconsidering Softmax and Linear Attention","created":"2024-12-09","cited_by_count":48},{"id":"2404.12224","title":"Length Generalization of Causal Transformers without Position Encoding","created":"2024-04-18","cited_by_count":47},{"id":"2402.03170","title":"Is Mamba Capable of In-Context Learning?","created":"2024-02-05","cited_by_count":45},{"id":"2410.02140","title":"A Formal Framework for Understanding Length Generalization in Transformers","created":"2024-10-03","cited_by_count":45},{"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":"2411.07635","title":"Breaking the Low-Rank Dilemma of Linear Attention","created":"2024-11-12","cited_by_count":31},{"id":"2502.02393","title":"Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers","created":"2025-02-04","cited_by_count":28},{"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},{"id":"2412.04703","title":"Transformers Struggle to Learn to Search","created":"2024-12-06","cited_by_count":19},{"id":"1412.0348","title":"Edit Distance Cannot Be Computed in Strongly Subquadratic Time (unless SETH is false)","created":"2014-12-01","cited_by_count":18},{"id":"2402.08132","title":"On the Resurgence of Recurrent Models for Long Sequences -- Survey and Research Opportunities in the Transformer Era","created":"2024-02-12","cited_by_count":17},{"id":"2506.00744","title":"Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers","created":"2025-05-31","cited_by_count":12},{"id":"2411.01992","title":"Ask, and it shall be given: On the Turing completeness of prompting","created":"2024-11-04","cited_by_count":10},{"id":"2410.04271","title":"Fundamental Limitations on Subquadratic Alternatives to Transformers","created":"2024-10-05","cited_by_count":9},{"id":"2505.03434","title":"Procedural Memory Is Not All You Need: Bridging Cognitive Gaps in LLM-Based Agents","created":"2025-05-06","cited_by_count":9},{"id":"2505.21785","title":"Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities","created":"2025-05-27","cited_by_count":6},{"id":"2507.15553","title":"Efficient Routing of Inference Requests across LLM Instances in Cloud-Edge Computing","created":"2025-07-21","cited_by_count":5},{"id":"2502.01578","title":"ReGLA: Refining Gated Linear Attention","created":"2025-02-03","cited_by_count":4},{"id":"2506.09316","title":"On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention","created":"2025-06-11","cited_by_count":3}],"next_cursor":null}