{"list":"other","total":95,"rows":[{"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":"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"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":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"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":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"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":"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":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"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":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666},{"id":"2111.09296","title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","created":"2021-11-17","cited_by_count":601},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502},{"id":"2006.13979","title":"Unsupervised Cross-lingual Representation Learning for Speech Recognition","created":"2020-06-24","cited_by_count":501},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476},{"id":"2003.05997","title":"Efficient Content-Based Sparse Attention with Routing Transformers","created":"2020-03-12","cited_by_count":471},{"id":"1912.07875","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","created":"2019-12-17","cited_by_count":467},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"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":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"1904.09925","title":"Attention Augmented Convolutional Networks","created":"2019-04-22","cited_by_count":363},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347},{"id":"1910.05453","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","created":"2019-10-12","cited_by_count":340},{"id":"2107.04734","title":"Layer-wise Analysis of a Self-supervised Speech Representation Model","created":"2021-07-10","cited_by_count":298},{"id":"2012.09816","title":"Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning","created":"2020-12-17","cited_by_count":297},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242},{"id":"1811.10959","title":"Dataset Distillation","created":"2018-11-27","cited_by_count":230},{"id":"2206.06522","title":"LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning","created":"2022-06-13","cited_by_count":230},{"id":"2010.10504","title":"Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition","created":"2020-10-20","cited_by_count":187},{"id":"2303.15647","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","created":"2023-03-28","cited_by_count":173},{"id":"1804.09541","title":"QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension","created":"2018-04-23","cited_by_count":164},{"id":"2211.03929","title":"Comparative layer-wise analysis of self-supervised speech models","created":"2022-11-08","cited_by_count":158},{"id":"2110.09327","title":"Self-Supervised Representation Learning: Introduction, Advances and Challenges","created":"2021-10-18","cited_by_count":148},{"id":"2110.01900","title":"DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT","created":"2021-10-05","cited_by_count":144},{"id":"2004.11886","title":"Lite Transformer with Long-Short Range Attention","created":"2020-04-24","cited_by_count":127},{"id":"2105.14103","title":"An Attention Free Transformer","created":"2021-05-28","cited_by_count":112},{"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":"2011.11588","title":"The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling","created":"2020-11-23","cited_by_count":101},{"id":"1910.09799","title":"Transformer-based Acoustic Modeling for Hybrid Speech Recognition","created":"2019-10-22","cited_by_count":88},{"id":"2103.12718","title":"Self-Supervised Pretraining Improves Self-Supervised Pretraining","created":"2021-03-23","cited_by_count":82},{"id":"2109.06870","title":"Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition","created":"2021-09-14","cited_by_count":68},{"id":"1912.05533","title":"SpecAugment on Large Scale Datasets","created":"2019-12-11","cited_by_count":60},{"id":"2106.05933","title":"PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition","created":"2021-06-10","cited_by_count":53},{"id":"2111.14706","title":"ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet","created":"2021-11-29","cited_by_count":53},{"id":"1803.08976","title":"Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speech","created":"2018-03-23","cited_by_count":52},{"id":"2203.15610","title":"LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT","created":"2022-03-29","cited_by_count":50},{"id":"1803.10225","title":"Light Gated Recurrent Units for Speech Recognition","created":"2018-03-26","cited_by_count":48},{"id":"2104.11462","title":"LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech","created":"2021-04-23","cited_by_count":47},{"id":"2104.14700","title":"The Zero Resource Speech Challenge 2021: Spoken language modelling","created":"2021-04-29","cited_by_count":47},{"id":"2305.10005","title":"DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning","created":"2023-05-17","cited_by_count":37},{"id":"2305.17651","title":"DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models","created":"2023-05-28","cited_by_count":36},{"id":"2010.13826","title":"Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining","created":"2020-10-26","cited_by_count":35},{"id":"1904.03107","title":"Convolutional Self-Attention Networks","created":"2019-04-05","cited_by_count":32},{"id":"2207.06867","title":"Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models","created":"2022-07-14","cited_by_count":31},{"id":"2302.14132","title":"Structured Pruning of Self-Supervised Pre-trained Models for Speech Recognition and Understanding","created":"2023-02-27","cited_by_count":31},{"id":"2007.01179","title":"Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models","created":"2020-07-02","cited_by_count":27},{"id":"2103.08393","title":"Wav2vec-C: A Self-supervised Model for Speech Representation Learning","created":"2021-03-09","cited_by_count":25},{"id":"2207.00555","title":"FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Learning","created":"2022-07-01","cited_by_count":25},{"id":"2104.07253","title":"Integration of Pre-trained Networks with Continuous Token Interface for End-to-End Spoken Language Understanding","created":"2021-04-15","cited_by_count":22},{"id":"2306.06672","title":"Reducing Barriers to Self-Supervised Learning: HuBERT Pre-training with Academic Compute","created":"2023-06-11","cited_by_count":21},{"id":"1910.01493","title":"From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition","created":"2019-10-02","cited_by_count":20},{"id":"2009.06097","title":"Cluster-Former: Clustering-based Sparse Transformer for Long-Range Dependency Encoding","created":"2020-09-13","cited_by_count":19},{"id":"2201.10207","title":"SPIRAL: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-Training","created":"2022-01-25","cited_by_count":19},{"id":"1510.08983","title":"Highway Long Short-Term Memory RNNs for Distant Speech Recognition","created":"2015-10-30","cited_by_count":17},{"id":"2110.04934","title":"Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition","created":"2021-10-11","cited_by_count":16},{"id":"2211.09944","title":"MelHuBERT: A simplified HuBERT on Mel spectrograms","created":"2022-11-17","cited_by_count":16},{"id":"2305.12213","title":"Taming Resource Heterogeneity In Distributed ML Training With Dynamic Batching","created":"2023-05-20","cited_by_count":12},{"id":"2204.02804","title":"Federated Self-supervised Speech Representations: Are We There Yet?","created":"2022-04-06","cited_by_count":10},{"id":"2204.11934","title":"On-demand compute reduction with stochastic wav2vec 2.0","created":"2022-04-25","cited_by_count":10},{"id":"2305.15348","title":"READ: Recurrent Adaptation of Large Transformers","created":"2023-05-24","cited_by_count":9},{"id":"2103.14583","title":"Leveraging pre-trained representations to improve access to untranscribed speech from endangered languages","created":"2021-03-26","cited_by_count":8},{"id":"2203.15840","title":"Autoregressive Co-Training for Learning Discrete Speech Representations","created":"2022-03-29","cited_by_count":8},{"id":"2210.09513","title":"Extracting speaker and emotion information from self-supervised speech models via channel-wise correlations","created":"2022-10-15","cited_by_count":7},{"id":"2209.15575","title":"Match to Win: Analysing Sequences Lengths for Efficient Self-supervised Learning in Speech and Audio","created":"2022-09-30","cited_by_count":6},{"id":"2211.05103","title":"Accidental Learners: Spoken Language Identification in Multilingual Self-Supervised Models","created":"2022-11-09","cited_by_count":6},{"id":"2302.10144","title":"Stabilising and accelerating light gated recurrent units for automatic speech recognition","created":"2023-02-16","cited_by_count":3}],"next_cursor":null}