{"list":"other","total":93,"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":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"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":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"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":"1704.04110","title":"DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks","created":"2017-04-13","cited_by_count":1013},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"2403.07815","title":"Chronos: Learning the Language of Time Series","created":"2024-03-12","cited_by_count":759},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"id":"2208.01066","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","created":"2022-08-01","cited_by_count":715},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601},{"id":"1705.03122","title":"Convolutional Sequence to Sequence Learning","created":"2017-05-08","cited_by_count":552},{"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":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2008.02217","title":"Hopfield Networks is All You Need","created":"2020-07-16","cited_by_count":475},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424},{"id":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408},{"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":"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":"1503.04069","title":"LSTM: A Search Space Odyssey","created":"2015-03-13","cited_by_count":316},{"id":"2306.00297","title":"Transformers learn to implement preconditioned gradient descent for in-context learning","created":"2023-06-01","cited_by_count":279},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265},{"id":"1906.01820","title":"Risks from Learned Optimization in Advanced Machine Learning Systems","created":"2019-06-05","cited_by_count":258},{"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":"1606.01164","title":"Dense Associative Memory for Pattern Recognition","created":"2016-06-03","cited_by_count":236},{"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":"2402.18668","title":"Simple linear attention language models balance the recall-throughput tradeoff","created":"2024-02-28","cited_by_count":208},{"id":"2312.04927","title":"Zoology: Measuring and Improving Recall in Efficient Language Models","created":"2023-12-08","cited_by_count":204},{"id":"2202.10447","title":"Transformer Quality in Linear Time","created":"2022-02-21","cited_by_count":191},{"id":"2309.14322","title":"Small-scale proxies for large-scale Transformer training instabilities","created":"2023-09-25","cited_by_count":183},{"id":"2306.00802","title":"Birth of a Transformer: A Memory Viewpoint","created":"2023-06-01","cited_by_count":161},{"id":"2404.05892","title":"Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence","created":"2024-04-08","cited_by_count":159},{"id":"2110.11945","title":"SOFT: Softmax-free Transformer with Linear Complexity","created":"2021-10-22","cited_by_count":128},{"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":"1903.08114","title":"Exact Gaussian Processes on a Million Data Points","created":"2019-03-19","cited_by_count":119},{"id":"2305.19420","title":"What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization","created":"2023-05-30","cited_by_count":118},{"id":"2202.12172","title":"Overcoming a Theoretical Limitation of Self-Attention","created":"2022-02-24","cited_by_count":113},{"id":"2008.06996","title":"Large Associative Memory Problem in Neurobiology and Machine Learning","created":"2020-08-16","cited_by_count":112},{"id":"2304.09433","title":"Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes","created":"2023-04-19","cited_by_count":111},{"id":"2405.16605","title":"Demystify Mamba in Vision: A Linear Attention Perspective","created":"2024-05-26","cited_by_count":102},{"id":"2309.05858","title":"Uncovering mesa-optimization algorithms in Transformers","created":"2023-09-11","cited_by_count":100},{"id":"2210.10340","title":"The Devil in Linear Transformer","created":"2022-10-19","cited_by_count":98},{"id":"2103.13076","title":"Finetuning Pretrained Transformers into RNNs","created":"2021-03-24","cited_by_count":96},{"id":"1907.01470","title":"Augmenting Self-attention with Persistent Memory","created":"2019-07-02","cited_by_count":93},{"id":"1611.01576","title":"Quasi-Recurrent Neural Networks","created":"2016-11-05","cited_by_count":87},{"id":"2111.00035","title":"Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\\\"om Method","created":"2021-10-29","cited_by_count":63},{"id":"2407.14207","title":"Longhorn: State Space Models are Amortized Online Learners","created":"2024-07-19","cited_by_count":59},{"id":"2202.04557","title":"Universal Hopfield Networks: A General Framework for Single-Shot Associative Memory Models","created":"2022-02-09","cited_by_count":55},{"id":"2412.06538","title":"Understanding Factual Recall in Transformers via Associative Memories","created":"2024-12-09","cited_by_count":51},{"id":"2311.01927","title":"GateLoop: Fully Data-Controlled Linear Recurrence for Sequence Modeling","created":"2023-11-03","cited_by_count":46},{"id":"2305.04749","title":"Toeplitz Neural Network for Sequence Modeling","created":"2023-05-08","cited_by_count":43},{"id":"2310.02984","title":"Scaling Laws for Associative Memories","created":"2023-10-04","cited_by_count":35},{"id":"1804.04849","title":"The unreasonable effectiveness of the forget gate","created":"2018-04-13","cited_by_count":34},{"id":"2308.06912","title":"CausalLM is not optimal for in-context learning","created":"2023-08-14","cited_by_count":26},{"id":"2212.02475","title":"Meta-Learning Fast Weight Language Models","created":"2022-12-05","cited_by_count":21},{"id":"2306.11197","title":"Sparse Modular Activation for Efficient Sequence Modeling","created":"2023-06-19","cited_by_count":20},{"id":"2312.06937","title":"Can a Transformer Represent a Kalman Filter?","created":"2023-12-12","cited_by_count":20},{"id":"2305.01638","title":"Sequence Modeling with Multiresolution Convolutional Memory","created":"2023-05-02","cited_by_count":19},{"id":"2212.14852","title":"An Analysis of Attention via the Lens of Exchangeability and Latent Variable Models","created":"2022-12-30","cited_by_count":16},{"id":"2403.19928","title":"DiJiang: Efficient Large Language Models through Compact Kernelization","created":"2024-03-29","cited_by_count":16},{"id":"2405.06394","title":"Memory Mosaics","created":"2024-05-10","cited_by_count":16},{"id":"2410.11135","title":"Mimetic Initialization Helps State Space Models Learn to Recall","created":"2024-10-14","cited_by_count":15},{"id":"2402.10644","title":"Linear Transformers with Learnable Kernel Functions are Better In-Context Models","created":"2024-02-16","cited_by_count":11},{"id":"2411.19574","title":"KV Shifting Attention Enhances Language Modeling","created":"2024-11-29","cited_by_count":8},{"id":"2305.10203","title":"Exploring the Space of Key-Value-Query Models with Intention","created":"2023-05-17","cited_by_count":7}],"next_cursor":null}