{"list":"other","total":105,"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":"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"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":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"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":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"1804.03209","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","created":"2018-04-09","cited_by_count":752},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"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":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666},{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643},{"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":"1912.10211","title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","created":"2019-12-21","cited_by_count":574},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2310.01889","title":"Ring Attention with Blockwise Transformers for Near-Infinite Context","created":"2023-10-03","cited_by_count":457},{"id":"1512.02595","title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","created":"2015-12-08","cited_by_count":451},{"id":"2401.04722","title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","created":"2024-01-09","cited_by_count":419},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347},{"id":"2108.06209","title":"W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training","created":"2021-08-07","cited_by_count":347},{"id":"2010.00475","title":"FSD50K: An Open Dataset of Human-Labeled Sound Events","created":"2020-10-01","cited_by_count":342},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328},{"id":"2405.04517","title":"xLSTM: Extended Long Short-Term Memory","created":"2024-05-07","cited_by_count":327},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273},{"id":"2403.09338","title":"LocalMamba: Visual State Space Model with Windowed Selective Scan","created":"2024-03-14","cited_by_count":236},{"id":"2110.05069","title":"Efficient Training of Audio Transformers with Patchout","created":"2021-10-11","cited_by_count":226},{"id":"1704.01279","title":"Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders","created":"2017-04-05","cited_by_count":225},{"id":"2305.11834","title":"Pengi: An Audio Language Model for Audio Tasks","created":"2023-05-19","cited_by_count":220},{"id":"1802.08435","title":"Efficient Neural Audio Synthesis","created":"2018-02-23","cited_by_count":219},{"id":"1910.12638","title":"Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders","created":"2019-10-25","cited_by_count":198},{"id":"1502.04623","title":"DRAW: A Recurrent Neural Network For Image Generation","created":"2015-02-16","cited_by_count":191},{"id":"2007.06028","title":"TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech","created":"2020-07-12","cited_by_count":188},{"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":"2010.10915","title":"Contrastive Learning of General-Purpose Audio Representations","created":"2020-10-21","cited_by_count":169},{"id":"2110.09784","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","created":"2021-10-19","cited_by_count":169},{"id":"2402.10739","title":"PointMamba: A Simple State Space Model for Point Cloud Analysis","created":"2024-02-16","cited_by_count":167},{"id":"2405.07992","title":"MambaOut: Do We Really Need Mamba for Vision?","created":"2024-05-13","cited_by_count":143},{"id":"2408.15237","title":"The Mamba in the Llama: Distilling and Accelerating Hybrid Models","created":"2024-08-27","cited_by_count":122},{"id":"2505.23719","title":"TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning","created":"2025-05-29","cited_by_count":120},{"id":"2206.10207","title":"SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders","created":"2022-06-21","cited_by_count":114},{"id":"2403.03234","title":"Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling","created":"2024-03-05","cited_by_count":113},{"id":"2212.07525","title":"Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language","created":"2022-12-14","cited_by_count":110},{"id":"2103.06695","title":"BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation","created":"2021-03-11","cited_by_count":106},{"id":"2402.05892","title":"Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data","created":"2024-02-08","cited_by_count":84},{"id":"2203.16691","title":"MAE-AST: Masked Autoencoding Audio Spectrogram Transformer","created":"2022-03-30","cited_by_count":82},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78},{"id":"2403.00762","title":"Point Cloud Mamba: Point Cloud Learning via State Space Model","created":"2024-03-01","cited_by_count":66},{"id":"2104.00769","title":"Keyword Transformer: A Self-Attention Model for Keyword Spotting","created":"2021-04-01","cited_by_count":60},{"id":"2204.12260","title":"Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representation","created":"2022-04-26","cited_by_count":52},{"id":"2406.04303","title":"Vision-LSTM: xLSTM as Generic Vision Backbone","created":"2024-06-06","cited_by_count":51},{"id":"2406.06992","title":"Scaling up masked audio encoder learning for general audio classification","created":"2024-06-11","cited_by_count":44},{"id":"2407.09941","title":"Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers","created":"2024-07-13","cited_by_count":44},{"id":"2501.15061","title":"PolaFormer: Polarity-aware Linear Attention for Vision Transformers","created":"2025-01-25","cited_by_count":32},{"id":"2307.02301","title":"Sumformer: Universal Approximation for Efficient Transformers","created":"2023-07-05","cited_by_count":30},{"id":"2408.10006","title":"Unlocking the Power of LSTM for Long Term Time Series Forecasting","created":"2024-08-19","cited_by_count":29},{"id":"2406.07537","title":"Autoregressive Pretraining with Mamba in Vision","created":"2024-06-11","cited_by_count":22},{"id":"2410.16928","title":"xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories","created":"2024-10-22","cited_by_count":19},{"id":"2503.13427","title":"xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference","created":"2025-03-17","cited_by_count":18},{"id":"2203.03691","title":"HyperMixer: An MLP-based Low Cost Alternative to Transformers","created":"2022-03-07","cited_by_count":13},{"id":"2411.04165","title":"Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences","created":"2024-11-06","cited_by_count":13},{"id":"2503.14376","title":"Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels","created":"2025-03-18","cited_by_count":13},{"id":"2407.01530","title":"xLSTM-UNet can be an Effective 2D & 3D Medical Image Segmentation Backbone with Vision-LSTM (ViL) better than its Mamba Counterpart","created":"2024-07-01","cited_by_count":12},{"id":"2410.00871","title":"MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining","created":"2024-10-01","cited_by_count":12},{"id":"2306.00561","title":"Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners","created":"2023-06-01","cited_by_count":11},{"id":"1712.04555","title":"Classification vs. Regression in Supervised Learning for Single Channel Speaker Count Estimation","created":"2017-12-12","cited_by_count":5},{"id":"2403.18560","title":"Noise-Robust Keyword Spotting through Self-supervised Pretraining","created":"2024-03-27","cited_by_count":5},{"id":"2406.14086","title":"Seg-LSTM: Performance of xLSTM for Semantic Segmentation of Remotely Sensed Images","created":"2024-06-20","cited_by_count":5},{"id":"2412.07804","title":"XLSTM-HVED: Cross-Modal Brain Tumor Segmentation and MRI Reconstruction Method Using Vision XLSTM and Heteromodal Variational Encoder-Decoder","created":"2024-12-09","cited_by_count":5},{"id":"2210.01703","title":"Improving Label-Deficient Keyword Spotting Through Self-Supervised Pretraining","created":"2022-10-04","cited_by_count":3},{"id":"2406.16993","title":"Are Vision xLSTM Embedded UNet More Reliable in Medical 3D Image Segmentation?","created":"2024-06-24","cited_by_count":3}],"next_cursor":"100"}