{"list":"other","total":85,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"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":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"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":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"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":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"2107.00630","title":"Variational Diffusion Models","created":"2021-07-01","cited_by_count":1153},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1702.03118","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","created":"2017-02-10","cited_by_count":950},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"1601.06759","title":"Pixel Recurrent Neural Networks","created":"2016-01-25","cited_by_count":816},{"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":"1911.05507","title":"Compressive Transformers for Long-Range Sequence Modelling","created":"2019-11-13","cited_by_count":726},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"id":"1704.04760","title":"In-Datacenter Performance Analysis of a Tensor Processing Unit","created":"2017-04-16","cited_by_count":618},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"2003.05997","title":"Efficient Content-Based Sparse Attention with Routing Transformers","created":"2020-03-12","cited_by_count":471},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"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":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"1707.08819","title":"A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets","created":"2017-07-27","cited_by_count":377},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347},{"id":"1801.10198","title":"Generating Wikipedia by Summarizing Long Sequences","created":"2018-01-30","cited_by_count":335},{"id":"2010.04245","title":"Query-Key Normalization for Transformers","created":"2020-10-08","cited_by_count":280},{"id":"1910.06764","title":"Stabilizing Transformers for Reinforcement Learning","created":"2019-10-13","cited_by_count":270},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265},{"id":"2002.11296","title":"Sparse Sinkhorn Attention","created":"2020-02-26","cited_by_count":251},{"id":"2212.09720","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","created":"2022-12-19","cited_by_count":251},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237},{"id":"2206.11253","title":"Towards Robust Blind Face Restoration with Codebook Lookup Transformer","created":"2022-06-22","cited_by_count":231},{"id":"2203.08913","title":"Memorizing Transformers","created":"2022-03-16","cited_by_count":226},{"id":"2202.08791","title":"cosFormer: Rethinking Softmax in Attention","created":"2022-02-17","cited_by_count":213},{"id":"2005.00743","title":"Synthesizer: Rethinking Self-Attention in Transformer Models","created":"2020-05-02","cited_by_count":205},{"id":"2207.06881","title":"Recurrent Memory Transformer","created":"2022-07-14","cited_by_count":203},{"id":"2202.10447","title":"Transformer Quality in Linear Time","created":"2022-02-21","cited_by_count":191},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179},{"id":"2305.07185","title":"MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers","created":"2023-05-12","cited_by_count":170},{"id":"1911.02972","title":"Blockwise Self-Attention for Long Document Understanding","created":"2019-11-07","cited_by_count":159},{"id":"2112.05682","title":"Self-attention Does Not Need $O(n^2)$ Memory","created":"2021-12-10","cited_by_count":154},{"id":"1905.07799","title":"Adaptive Attention Span in Transformers","created":"2019-05-19","cited_by_count":149},{"id":"1907.05242","title":"Large Memory Layers with Product Keys","created":"2019-07-10","cited_by_count":124},{"id":"2007.04825","title":"Fast Transformers with Clustered Attention","created":"2020-07-09","cited_by_count":123},{"id":"2203.07852","title":"Block-Recurrent Transformers","created":"2022-03-11","cited_by_count":110},{"id":"1803.03382","title":"Fast Decoding in Sequence Models using Discrete Latent Variables","created":"2018-03-09","cited_by_count":104},{"id":"2107.02192","title":"Long-Short Transformer: Efficient Transformers for Language and Vision","created":"2021-07-05","cited_by_count":102},{"id":"2110.13711","title":"Hierarchical Transformers Are More Efficient Language Models","created":"2021-10-26","cited_by_count":102},{"id":"2210.10340","title":"The Devil in Linear Transformer","created":"2022-10-19","cited_by_count":98},{"id":"2106.01540","title":"Luna: Linear Unified Nested Attention","created":"2021-06-03","cited_by_count":96},{"id":"1907.01470","title":"Augmenting Self-attention with Persistent Memory","created":"2019-07-02","cited_by_count":93},{"id":"2109.09115","title":"Do Long-Range Language Models Actually Use Long-Range Context?","created":"2021-09-19","cited_by_count":92},{"id":"2211.09761","title":"Efficient Transformers with Dynamic Token Pooling","created":"2022-11-17","cited_by_count":76},{"id":"2107.05768","title":"Combiner: Full Attention Transformer with Sparse Computation Cost","created":"2021-07-12","cited_by_count":64},{"id":"2202.07765","title":"General-purpose, long-context autoregressive modeling with Perceiver AR","created":"2022-02-15","cited_by_count":60},{"id":"2106.04627","title":"Densely connected normalizing flows","created":"2021-06-08","cited_by_count":49},{"id":"2107.11906","title":"H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences","created":"2021-07-25","cited_by_count":47},{"id":"1911.04070","title":"BP-Transformer: Modelling Long-Range Context via Binary Partitioning","created":"2019-11-11","cited_by_count":38},{"id":"2111.10493","title":"Discrete Representations Strengthen Vision Transformer Robustness","created":"2021-11-20","cited_by_count":35},{"id":"2102.12459","title":"When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute","created":"2021-02-24","cited_by_count":34},{"id":"2105.06548","title":"Not All Memories are Created Equal: Learning to Forget by Expiring","created":"2021-05-13","cited_by_count":32},{"id":"2203.13751","title":"Efficient-VDVAE: Less is more","created":"2022-03-25","cited_by_count":26},{"id":"2009.06097","title":"Cluster-Former: Clustering-based Sparse Transformer for Long-Range Dependency Encoding","created":"2020-09-13","cited_by_count":19},{"id":"2207.06366","title":"N-Grammer: Augmenting Transformers with latent n-grams","created":"2022-07-13","cited_by_count":14},{"id":"2305.14952","title":"Focus Your Attention (with Adaptive IIR Filters)","created":"2023-05-24","cited_by_count":12},{"id":"1908.10396","title":"Accelerating Large-Scale Inference with Anisotropic Vector Quantization","created":"2019-08-27","cited_by_count":9}],"next_cursor":null}