{"list":"other","total":65,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"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":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"1801.07606","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","created":"2018-01-22","cited_by_count":1102},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"2211.09527","title":"Ignore Previous Prompt: Attack Techniques For Language Models","created":"2022-11-17","cited_by_count":832},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"2006.05205","title":"On the Bottleneck of Graph Neural Networks and its Practical Implications","created":"2020-06-09","cited_by_count":631},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"id":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2111.14522","title":"Understanding over-squashing and bottlenecks on graphs via curvature","created":"2021-11-29","cited_by_count":478},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424},{"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},{"id":"2406.11794","title":"DataComp-LM: In search of the next generation of training sets for language models","created":"2024-06-17","cited_by_count":398},{"id":"2406.06484","title":"Parallelizing Linear Transformers with the Delta Rule over Sequence Length","created":"2024-06-10","cited_by_count":396},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"2405.04517","title":"xLSTM: Extended Long Short-Term Memory","created":"2024-05-07","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":"1905.09550","title":"Revisiting Graph Neural Networks: All We Have is Low-Pass Filters","created":"2019-05-23","cited_by_count":261},{"id":"2006.13318","title":"A Note on Over-Smoothing for Graph Neural Networks","created":"2020-06-23","cited_by_count":249},{"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":"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":"2312.04927","title":"Zoology: Measuring and Improving Recall in Efficient Language Models","created":"2023-12-08","cited_by_count":204},{"id":"2404.08819","title":"The Illusion of State in State-Space Models","created":"2024-04-12","cited_by_count":187},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179},{"id":"2202.09729","title":"It's Raw! Audio Generation with State-Space Models","created":"2022-02-20","cited_by_count":171},{"id":"2302.02941","title":"On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology","created":"2023-02-06","cited_by_count":166},{"id":"2312.10794","title":"A mathematical perspective on Transformers","created":"2023-12-17","cited_by_count":164},{"id":"2404.05892","title":"Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence","created":"2024-04-08","cited_by_count":159},{"id":"2203.05962","title":"Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice","created":"2022-03-09","cited_by_count":136},{"id":"2212.10554","title":"A Length-Extrapolatable Transformer","created":"2022-12-20","cited_by_count":127},{"id":"2404.07904","title":"HGRN2: Gated Linear RNNs with State Expansion","created":"2024-04-11","cited_by_count":127},{"id":"2402.04347","title":"The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry","created":"2024-02-06","cited_by_count":120},{"id":"2210.09298","title":"What Makes Convolutional Models Great on Long Sequence Modeling?","created":"2022-10-17","cited_by_count":87},{"id":"2202.08625","title":"Revisiting Over-smoothing in BERT from the Perspective of Graph","created":"2022-02-17","cited_by_count":72},{"id":"2403.17844","title":"Mechanistic Design and Scaling of Hybrid Architectures","created":"2024-03-26","cited_by_count":59},{"id":"2212.10701","title":"A Non-Asymptotic Analysis of Oversmoothing in Graph Neural Networks","created":"2022-12-21","cited_by_count":49},{"id":"2305.16102","title":"Demystifying Oversmoothing in Attention-Based Graph Neural Networks","created":"2023-05-25","cited_by_count":49},{"id":"2405.18781","title":"On the Role of Attention Masks and LayerNorm in Transformers","created":"2024-05-29","cited_by_count":48},{"id":"2404.08801","title":"Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length","created":"2024-04-12","cited_by_count":46},{"id":"2309.13414","title":"State-space Models with Layer-wise Nonlinearity are Universal Approximators with Exponential Decaying Memory","created":"2023-09-23","cited_by_count":39},{"id":"2410.01201","title":"Were RNNs All We Needed?","created":"2024-10-02","cited_by_count":38},{"id":"1804.04849","title":"The unreasonable effectiveness of the forget gate","created":"2018-04-13","cited_by_count":34}],"next_cursor":null}