{"total":85,"rows":[{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"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":"2103.06332","title":"Hurdles to Progress in Long-form Question Answering","created":"2021-03-10","cited_by_count":167,"area":null},{"id":"2109.08668","title":"Primer: Searching for Efficient Transformers for Language Modeling","created":"2021-09-17","cited_by_count":164,"area":null},{"id":"2103.13262","title":"FastMoE: A Fast Mixture-of-Expert Training System","created":"2021-03-24","cited_by_count":112,"area":"moe"},{"id":"2106.15115","title":"Neural Machine Translation for Low-Resource Languages: A Survey","created":"2021-06-29","cited_by_count":109,"area":null},{"id":"2106.01540","title":"Luna: Linear Unified Nested Attention","created":"2021-06-03","cited_by_count":96,"area":null},{"id":"2102.11972","title":"Do Transformer Modifications Transfer Across Implementations and Applications?","created":"2021-02-23","cited_by_count":87,"area":null},{"id":"2301.13852","title":"ChatGPT or Human? Detect and Explain. Explaining Decisions of Machine Learning Model for Detecting Short ChatGPT-generated Text","created":"2023-01-30","cited_by_count":85,"area":null},{"id":"2305.15805","title":"Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers","created":"2023-05-25","cited_by_count":67,"area":null},{"id":"2202.07765","title":"General-purpose, long-context autoregressive modeling with Perceiver AR","created":"2022-02-15","cited_by_count":60,"area":null},{"id":"2105.13318","title":"Synthetic Data Generation for Grammatical Error Correction with Tagged Corruption Models","created":"2021-05-27","cited_by_count":56,"area":null},{"id":"2305.03210","title":"AttentionViz: A Global View of Transformer Attention","created":"2023-05-04","cited_by_count":50,"area":null},{"id":"2110.03036","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","created":"2021-10-06","cited_by_count":47,"area":null},{"id":"2304.04052","title":"Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder","created":"2023-04-08","cited_by_count":44,"area":null},{"id":"2104.08154","title":"Counter-Interference Adapter for Multilingual Machine Translation","created":"2021-04-16","cited_by_count":40,"area":null},{"id":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39,"area":null},{"id":"2210.06929","title":"On the Explainability of Natural Language Processing Deep Models","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2104.08698","title":"A Simple and Effective Positional Encoding for Transformers","created":"2021-04-18","cited_by_count":37,"area":null},{"id":"2110.06821","title":"Leveraging redundancy in attention with Reuse Transformers","created":"2021-10-13","cited_by_count":33,"area":null},{"id":"2104.00290","title":"Many-to-English Machine Translation Tools, Data, and Pretrained Models","created":"2021-04-01","cited_by_count":31,"area":null},{"id":"2102.02340","title":"MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records","created":"2021-02-03","cited_by_count":30,"area":null},{"id":"2104.07429","title":"First the worst: Finding better gender translations during beam search","created":"2021-04-15","cited_by_count":29,"area":null},{"id":"2103.06450","title":"Full Page Handwriting Recognition via Image to Sequence Extraction","created":"2021-03-11","cited_by_count":24,"area":null},{"id":"2105.07205","title":"Rethinking Skip Connection with Layer Normalization in Transformers and ResNets","created":"2021-05-15","cited_by_count":22,"area":null},{"id":"2106.01506","title":"Transformers are Deep Infinite-Dimensional Non-Mercer Binary Kernel Machines","created":"2021-06-02","cited_by_count":22,"area":null},{"id":"2102.09754","title":"VisuoSpatial Foresight for Physical Sequential Fabric Manipulation","created":"2021-02-19","cited_by_count":18,"area":null},{"id":"2102.07298","title":"A Deep Adversarial Model for Suffix and Remaining Time Prediction of Event Sequences","created":"2021-02-15","cited_by_count":17,"area":null},{"id":"2105.13072","title":"TranSmart: A Practical Interactive Machine Translation System","created":"2021-05-27","cited_by_count":17,"area":null},{"id":"2206.11925","title":"Set Norm and Equivariant Skip Connections: Putting the Deep in Deep Sets","created":"2022-06-23","cited_by_count":17,"area":null},{"id":"2205.10095","title":"How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processing","created":"2022-05-20","cited_by_count":16,"area":null},{"id":"2206.00330","title":"B2T Connection: Serving Stability and Performance in Deep Transformers","created":"2022-06-01","cited_by_count":16,"area":null},{"id":"2101.02046","title":"TextBox: A Unified, Modularized, and Extensible Framework for Text Generation","created":"2021-01-06","cited_by_count":15,"area":null},{"id":"2111.09451","title":"Benchmarking and scaling of deep learning models for land cover image classification","created":"2021-11-18","cited_by_count":14,"area":null},{"id":"2105.00388","title":"Billion-scale Pre-trained E-commerce Product Knowledge Graph Model","created":"2021-05-02","cited_by_count":13,"area":null},{"id":"2111.10746","title":"Capitalization and Punctuation Restoration: a Survey","created":"2021-11-21","cited_by_count":13,"area":null},{"id":"2205.01133","title":"Hausa Visual Genome: A Dataset for Multi-Modal English to Hausa Machine Translation","created":"2022-05-02","cited_by_count":13,"area":null},{"id":"2305.17690","title":"HaVQA: A Dataset for Visual Question Answering and Multimodal Research in Hausa Language","created":"2023-05-28","cited_by_count":12,"area":null},{"id":"2104.03543","title":"Extended Parallel Corpus for Amharic-English Machine Translation","created":"2021-04-08","cited_by_count":10,"area":null},{"id":"2204.05424","title":"A Call for Clarity in Beam Search: How It Works and When It Stops","created":"2022-04-11","cited_by_count":10,"area":null},{"id":"2303.16028","title":"Synthetically generated text for supervised text analysis","created":"2023-03-28","cited_by_count":10,"area":null},{"id":"2105.05977","title":"Spelling Correction with Denoising Transformer","created":"2021-05-12","cited_by_count":9,"area":null},{"id":"2108.03509","title":"Compositional Generalization in Multilingual Semantic Parsing over Wikidata","created":"2021-08-07","cited_by_count":9,"area":null},{"id":"2302.05794","title":"Mutation-Based Adversarial Attacks on Neural Text Detectors","created":"2023-02-11","cited_by_count":9,"area":null},{"id":"2304.14395","title":"string2string: A Modern Python Library for String-to-String Algorithms","created":"2023-04-27","cited_by_count":9,"area":null},{"id":"2308.00683","title":"CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code","created":"2023-08-01","cited_by_count":9,"area":null},{"id":"2204.13021","title":"NLU++: A Multi-Label, Slot-Rich, Generalisable Dataset for Natural Language Understanding in Task-Oriented Dialogue","created":"2022-04-27","cited_by_count":8,"area":null},{"id":"2108.11126","title":"YANMTT: Yet Another Neural Machine Translation Toolkit","created":"2021-08-25","cited_by_count":7,"area":null},{"id":"2111.07592","title":"Say What? Collaborative Pop Lyric Generation Using Multitask Transfer Learning","created":"2021-11-15","cited_by_count":7,"area":null},{"id":"2312.00100","title":"Introducing Rhetorical Parallelism Detection: A New Task with Datasets, Metrics, and Baselines","created":"2023-11-30","cited_by_count":7,"area":null},{"id":"2104.00120","title":"Multi-Encoder Learning and Stream Fusion for Transformer-Based End-to-End Automatic Speech Recognition","created":"2021-03-31","cited_by_count":6,"area":null},{"id":"2105.04779","title":"EL-Attention: Memory Efficient Lossless Attention for Generation","created":"2021-05-11","cited_by_count":6,"area":null},{"id":"2304.02282","title":"About optimal loss function for training physics-informed neural networks under respecting causality","created":"2023-04-05","cited_by_count":6,"area":null},{"id":"2401.13486","title":"Separable Physics-Informed Neural Networks for the solution of elasticity problems","created":"2024-01-24","cited_by_count":6,"area":null},{"id":"2102.00826","title":"Automated Query Reformulation for Efficient Search based on Query Logs From Stack Overflow","created":"2021-02-01","cited_by_count":4,"area":null},{"id":"2205.01848","title":"Optimizing Mixture of Experts using Dynamic Recompilations","created":"2022-05-04","cited_by_count":4,"area":"moe"},{"id":"2505.11664","title":"A Local Polyak-Lojasiewicz and Descent Lemma of Gradient Descent For Overparametrized Linear Models","created":"2025-05-16","cited_by_count":4,"area":null},{"id":"2104.08364","title":"Sync-Switch: Hybrid Parameter Synchronization for Distributed Deep Learning","created":"2021-04-16","cited_by_count":3,"area":null},{"id":"2109.07343","title":"Mi{\\dh}eind's WMT 2021 submission","created":"2021-09-15","cited_by_count":3,"area":null},{"id":"2305.09312","title":"Exploring the Impact of Layer Normalization for Zero-shot Neural Machine Translation","created":"2023-05-16","cited_by_count":3,"area":null},{"id":"2210.03405","title":"PARAGEN : A Parallel Generation Toolkit","created":"2022-10-07","cited_by_count":2,"area":null},{"id":"2212.00486","title":"CUNI Systems for the WMT22 Czech-Ukrainian Translation Task","created":"2022-12-01","cited_by_count":2,"area":null},{"id":"2412.17537","title":"Domain adapted machine translation: What does catastrophic forgetting forget and why?","created":"2024-12-23","cited_by_count":2,"area":null},{"id":"2508.10368","title":"Large Language Models for Summarizing Czech Historical Documents and Beyond","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2510.00662","title":"Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generation","created":"2025-10-01","cited_by_count":2,"area":null},{"id":"2105.04888","title":"Hierarchical RNNs-Based Transformers MADDPG for Mixed Cooperative-Competitive Environments","created":"2021-05-11","cited_by_count":1,"area":null},{"id":"2108.12768","title":"CrossedWires: A Dataset of Syntactically Equivalent but Semantically Disparate Deep Learning Models","created":"2021-08-29","cited_by_count":1,"area":null},{"id":"2209.11963","title":"A Deep Investigation of RNN and Self-attention for the Cyrillic-Traditional Mongolian Bidirectional Conversion","created":"2022-09-24","cited_by_count":1,"area":null},{"id":"2307.05799","title":"3D Medical Image Segmentation based on multi-scale MPU-Net","created":"2023-07-11","cited_by_count":1,"area":null},{"id":"2410.13318","title":"Computational Approaches to Arabic-English Code-Switching","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2603.14756","title":"Towards Privacy-Preserving Machine Translation at the Inference Stage: A New Task and Benchmark","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2104.05547","title":"WHOSe Heritage: Classification of UNESCO World Heritage \"Outstanding Universal Value\" Documents with Soft Labels","created":"2021-04-12","cited_by_count":0,"area":null},{"id":"2107.14590","title":"Residual Tree Aggregation of Layers for Neural Machine Translation","created":"2021-07-19","cited_by_count":0,"area":null},{"id":"2210.12310","title":"Tools for Extracting Spatio-Temporal Patterns in Meteorological Image Sequences: From Feature Engineering to Attention-Based Neural Networks","created":"2022-10-22","cited_by_count":0,"area":null},{"id":"2210.17262","title":"QNet: A Quantum-native Sequence Encoder Architecture","created":"2022-10-31","cited_by_count":0,"area":null},{"id":"2409.02965","title":"Do We Trust What They Say or What They Do? A Multimodal User Embedding Provides Personalized Explanations","created":"2024-09-04","cited_by_count":0,"area":null},{"id":"2410.15144","title":"A survey of neural-network-based methods utilising comparable data for finding translation equivalents","created":"2024-10-19","cited_by_count":0,"area":null},{"id":"2410.18430","title":"Building Dialogue Understanding Models for Low-resource Language Indonesian from Scratch","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2501.09611","title":"EVaDE : Event-Based Variational Thompson Sampling for Model-Based Reinforcement Learning","created":"2025-01-16","cited_by_count":0,"area":"deeprl"},{"id":"2502.19983","title":"Efficient Time Series Forecasting via Hyper-Complex Models and Frequency Aggregation","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2505.13102","title":"Lightweight and Interpretable Transformer via Mixed Graph Algorithm Unrolling for Traffic Forecast","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2510.14136","title":"A Multimodal Approach to Heritage Preservation in the Context of Climate Change","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2511.18848","title":"Large Language Models for the Summarization of Czech Documents: From History to the Present","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2602.20749","title":"Explicit Grammar Semantic Feature Fusion for Robust Text Classification","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2606.20087","title":"Multi-Head Attention-Based Feature Extractor Integration with Soft Actor-Critic for Porosity Prediction and Process Parameter Optimization in Additive Manufacturing","created":"2026-06-18","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}