{"total":1488,"rows":[{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297,"area":"rag"},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703,"area":null},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342,"area":null},{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906,"area":null},{"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,"area":null},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649,"area":null},{"id":"2111.09296","title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","created":"2021-11-17","cited_by_count":601,"area":null},{"id":"2210.10341","title":"BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining","created":"2022-10-19","cited_by_count":538,"area":null},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502,"area":null},{"id":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498,"area":null},{"id":"2101.00390","title":"VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation","created":"2021-01-02","cited_by_count":463,"area":null},{"id":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439,"area":null},{"id":"2305.13516","title":"Scaling Speech Technology to 1,000+ Languages","created":"2023-05-22","cited_by_count":411,"area":null},{"id":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406,"area":null},{"id":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403,"area":null},{"id":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366,"area":null},{"id":"2104.02112","title":"Efficient Attentions for Long Document Summarization","created":"2021-04-05","cited_by_count":345,"area":null},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340,"area":null},{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288,"area":null},{"id":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287,"area":null},{"id":"2109.10282","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","created":"2021-09-21","cited_by_count":279,"area":null},{"id":"2112.10668","title":"Few-shot Learning with Multilingual Language Models","created":"2021-12-20","cited_by_count":278,"area":null},{"id":"2410.17891","title":"Scaling Diffusion Language Models via Adaptation from Autoregressive Models","created":"2024-10-23","cited_by_count":274,"area":"diffusion"},{"id":"2311.04934","title":"Prompt Cache: Modular Attention Reuse for Low-Latency Inference","created":"2023-11-07","cited_by_count":268,"area":null},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237,"area":null},{"id":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237,"area":"moe"},{"id":"2107.07653","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","created":"2021-07-16","cited_by_count":235,"area":null},{"id":"2104.08378","title":"Accelerating Sparse Deep Neural Networks","created":"2021-04-16","cited_by_count":223,"area":null},{"id":"2205.10770","title":"Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models","created":"2022-05-22","cited_by_count":220,"area":null},{"id":"2106.14448","title":"R-Drop: Regularized Dropout for Neural Networks","created":"2021-06-28","cited_by_count":202,"area":null},{"id":"2206.03382","title":"Tutel: Adaptive Mixture-of-Experts at Scale","created":"2022-06-07","cited_by_count":201,"area":"moe"},{"id":"2102.07033","title":"PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them","created":"2021-02-13","cited_by_count":200,"area":null},{"id":"2110.03370","title":"WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition","created":"2021-10-07","cited_by_count":197,"area":null},{"id":"2208.03306","title":"Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models","created":"2022-08-05","cited_by_count":191,"area":null},{"id":"2104.08826","title":"GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation","created":"2021-04-18","cited_by_count":187,"area":null},{"id":"2203.17189","title":"Scaling Up Models and Data with $\\texttt{t5x}$ and $\\texttt{seqio}$","created":"2022-03-31","cited_by_count":187,"area":null},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180,"area":null},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179,"area":null},{"id":"2104.06644","title":"Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little","created":"2021-04-14","cited_by_count":177,"area":null},{"id":"2103.15025","title":"On Hallucination and Predictive Uncertainty in Conditional Language Generation","created":"2021-03-28","cited_by_count":176,"area":null},{"id":"2112.10684","title":"Efficient Large Scale Language Modeling with Mixtures of Experts","created":"2021-12-20","cited_by_count":175,"area":"moe"},{"id":"2208.06677","title":"Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models","created":"2022-08-13","cited_by_count":174,"area":null},{"id":"2104.06683","title":"The Curious Case of Hallucinations in Neural Machine Translation","created":"2021-04-14","cited_by_count":161,"area":null},{"id":"2303.06296","title":"Stabilizing Transformer Training by Preventing Attention Entropy Collapse","created":"2023-03-11","cited_by_count":161,"area":null},{"id":"2302.05737","title":"A Reparameterized Discrete Diffusion Model for Text Generation","created":"2023-02-11","cited_by_count":152,"area":"diffusion"},{"id":"2203.16634","title":"Transformer Language Models without Positional Encodings Still Learn Positional Information","created":"2022-03-30","cited_by_count":150,"area":null},{"id":"2107.05604","title":"Direct speech-to-speech translation with discrete units","created":"2021-07-12","cited_by_count":149,"area":null},{"id":"2105.11084","title":"Unsupervised Speech Recognition","created":"2021-05-24","cited_by_count":148,"area":null},{"id":"2205.06266","title":"Lifting the Curse of Multilinguality by Pre-training Modular Transformers","created":"2022-05-12","cited_by_count":146,"area":null},{"id":"2305.05920","title":"Fast Distributed Inference Serving for Large Language Models","created":"2023-05-10","cited_by_count":145,"area":"inference"},{"id":"2110.01900","title":"DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT","created":"2021-10-05","cited_by_count":144,"area":null},{"id":"2201.07520","title":"CM3: A Causal Masked Multimodal Model of the Internet","created":"2022-01-19","cited_by_count":142,"area":null},{"id":"2204.07580","title":"mGPT: Few-Shot Learners Go Multilingual","created":"2022-04-15","cited_by_count":142,"area":null},{"id":"2206.03126","title":"Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse","created":"2022-06-07","cited_by_count":141,"area":null},{"id":"2110.11773","title":"Sinkformers: Transformers with Doubly Stochastic Attention","created":"2021-10-22","cited_by_count":138,"area":null},{"id":"2104.05596","title":"Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages","created":"2021-04-12","cited_by_count":136,"area":null},{"id":"2301.10921","title":"SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning","created":"2023-01-26","cited_by_count":133,"area":null},{"id":"2102.06203","title":"Proof Artifact Co-training for Theorem Proving with Language Models","created":"2021-02-11","cited_by_count":132,"area":"offlinerl"},{"id":"2108.05036","title":"DEMix Layers: Disentangling Domains for Modular Language Modeling","created":"2021-08-11","cited_by_count":132,"area":null},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"area":null},{"id":"2208.12266","title":"Decoding speech perception from non-invasive brain recordings","created":"2022-08-25","cited_by_count":130,"area":null},{"id":"2109.09784","title":"Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization","created":"2021-08-30","cited_by_count":129,"area":null},{"id":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129,"area":null},{"id":"2303.16104","title":"Hallucinations in Large Multilingual Translation Models","created":"2023-03-28","cited_by_count":129,"area":null},{"id":"2102.08473","title":"COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining","created":"2021-02-16","cited_by_count":126,"area":null},{"id":"2203.16502","title":"Generative Spoken Dialogue Language Modeling","created":"2022-03-30","cited_by_count":126,"area":null},{"id":"2403.09054","title":"Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference","created":"2024-03-14","cited_by_count":126,"area":"inference"},{"id":"2111.09509","title":"How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN","created":"2021-11-18","cited_by_count":124,"area":null},{"id":"2201.05273","title":"Pretrained Language Models for Text Generation: A Survey","created":"2022-01-14","cited_by_count":122,"area":null},{"id":"2112.08352","title":"Textless Speech-to-Speech Translation on Real Data","created":"2021-12-15","cited_by_count":121,"area":null},{"id":"2109.09209","title":"CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization","created":"2021-09-19","cited_by_count":120,"area":null},{"id":"2102.09130","title":"Entity-level Factual Consistency of Abstractive Text Summarization","created":"2021-02-18","cited_by_count":118,"area":null},{"id":"2202.08005","title":"Should You Mask 15% in Masked Language Modeling?","created":"2022-02-16","cited_by_count":118,"area":null},{"id":"2110.04260","title":"Taming Sparsely Activated Transformer with Stochastic Experts","created":"2021-10-08","cited_by_count":113,"area":"moe"},{"id":"2205.12674","title":"Training Language Models with Memory Augmentation","created":"2022-05-25","cited_by_count":113,"area":null},{"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,"area":null},{"id":"2106.15115","title":"Neural Machine Translation for Low-Resource Languages: A Survey","created":"2021-06-29","cited_by_count":109,"area":null},{"id":"2102.01757","title":"The Multilingual TEDx Corpus for Speech Recognition and Translation","created":"2021-02-02","cited_by_count":101,"area":null},{"id":"2107.07455","title":"Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks","created":"2021-07-15","cited_by_count":101,"area":null},{"id":"2106.03794","title":"COVID-Fact: Fact Extraction and Verification of Real-World Claims on COVID-19 Pandemic","created":"2021-06-07","cited_by_count":100,"area":null},{"id":"2205.02022","title":"A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation","created":"2022-05-04","cited_by_count":98,"area":null},{"id":"2210.10340","title":"The Devil in Linear Transformer","created":"2022-10-19","cited_by_count":98,"area":null},{"id":"2103.13076","title":"Finetuning Pretrained Transformers into RNNs","created":"2021-03-24","cited_by_count":96,"area":null},{"id":"2106.01540","title":"Luna: Linear Unified Nested Attention","created":"2021-06-03","cited_by_count":96,"area":null},{"id":"2206.02369","title":"Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation","created":"2022-06-06","cited_by_count":94,"area":null},{"id":"2403.15796","title":"Understanding Emergent Abilities of Language Models from the Loss Perspective","created":"2024-03-23","cited_by_count":94,"area":null},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2105.00164","title":"Hidden Backdoors in Human-Centric Language Models","created":"2021-05-01","cited_by_count":90,"area":"safety"},{"id":"2302.03162","title":"Protecting Language Generation Models via Invisible Watermarking","created":"2023-02-06","cited_by_count":90,"area":"safety"},{"id":"2306.07915","title":"Image Captioners Are Scalable Vision Learners Too","created":"2023-06-13","cited_by_count":89,"area":"mllm"},{"id":"2301.10472","title":"XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models","created":"2023-01-25","cited_by_count":88,"area":null},{"id":"2311.15566","title":"SpotServe: Serving Generative Large Language Models on Preemptible Instances","created":"2023-11-27","cited_by_count":87,"area":"inference"},{"id":"2103.00073","title":"CURE: Code-Aware Neural Machine Translation for Automatic Program Repair","created":"2021-02-26","cited_by_count":86,"area":null},{"id":"2103.01197","title":"Coordination Among Neural Modules Through a Shared Global Workspace","created":"2021-03-01","cited_by_count":85,"area":null},{"id":"2112.02701","title":"Protecting Intellectual Property of Language Generation APIs with Lexical Watermark","created":"2021-12-05","cited_by_count":84,"area":"safety"},{"id":"2110.09456","title":"NormFormer: Improved Transformer Pretraining with Extra Normalization","created":"2021-10-18","cited_by_count":83,"area":null},{"id":"2203.16691","title":"MAE-AST: Masked Autoencoding Audio Spectrogram Transformer","created":"2022-03-30","cited_by_count":82,"area":null}],"next_cursor":"100"}