{"total":85,"rows":[{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703,"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":"2403.08763","title":"Simple and Scalable Strategies to Continually Pre-train Large Language Models","created":"2024-03-13","cited_by_count":127,"area":null},{"id":"2207.14484","title":"Adaptive Gradient Methods at the Edge of Stability","created":"2022-07-29","cited_by_count":101,"area":null},{"id":"2106.10207","title":"Distributed Deep Learning in Open Collaborations","created":"2021-06-18","cited_by_count":58,"area":null},{"id":"2202.03896","title":"Speech Emotion Recognition using Self-Supervised Features","created":"2022-02-07","cited_by_count":53,"area":null},{"id":"2104.06951","title":"Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey","created":"2021-04-14","cited_by_count":46,"area":null},{"id":"2205.01138","title":"Transformers in Time-series Analysis: A Tutorial","created":"2022-04-28","cited_by_count":46,"area":null},{"id":"2105.08316","title":"CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation","created":"2021-05-18","cited_by_count":42,"area":null},{"id":"2103.11647","title":"Prototypical Representation Learning for Relation Extraction","created":"2021-03-22","cited_by_count":33,"area":null},{"id":"2502.19002","title":"The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training","created":"2025-02-26","cited_by_count":30,"area":null},{"id":"2110.08191","title":"Why don't people use character-level machine translation?","created":"2021-10-15","cited_by_count":27,"area":null},{"id":"2112.15210","title":"Persformer: A Transformer Architecture for Topological Machine Learning","created":"2021-12-30","cited_by_count":19,"area":null},{"id":"2402.07193","title":"Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent","created":"2024-02-11","cited_by_count":19,"area":null},{"id":"2204.06340","title":"Distributionally Robust Models with Parametric Likelihood Ratios","created":"2022-04-13","cited_by_count":17,"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":"2210.11803","title":"Revisiting Checkpoint Averaging for Neural Machine Translation","created":"2022-10-21","cited_by_count":13,"area":null},{"id":"2103.17151","title":"Divide and Rule: Effective Pre-Training for Context-Aware Multi-Encoder Translation Models","created":"2021-03-31","cited_by_count":12,"area":null},{"id":"2105.00813","title":"Transformers: \"The End of History\" for NLP?","created":"2021-04-09","cited_by_count":12,"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":"2111.02574","title":"Contextual Semantic Parsing for Multilingual Task-Oriented Dialogues","created":"2021-11-04","cited_by_count":10,"area":null},{"id":"2205.05862","title":"AdaVAE: Exploring Adaptive GPT-2s in Variational Auto-Encoders for Language Modeling","created":"2022-05-12","cited_by_count":10,"area":null},{"id":"2410.10897","title":"EPi-cKANs: Elasto-Plasticity Informed Kolmogorov-Arnold Networks Using Chebyshev Polynomials","created":"2024-10-12","cited_by_count":9,"area":null},{"id":"2410.10986","title":"What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis","created":"2024-10-14","cited_by_count":9,"area":null},{"id":"2108.00596","title":"GTNet:Guided Transformer Network for Detecting Human-Object Interactions","created":"2021-08-02","cited_by_count":8,"area":null},{"id":"2201.12926","title":"Compositionality as Lexical Symmetry","created":"2022-01-30","cited_by_count":8,"area":null},{"id":"2304.08968","title":"Stochastic Parrots Looking for Stochastic Parrots: LLMs are Easy to Fine-Tune and Hard to Detect with other LLMs","created":"2023-04-18","cited_by_count":8,"area":null},{"id":"2305.16834","title":"Free Lunch: Robust Cross-Lingual Transfer via Model Checkpoint Averaging","created":"2023-05-26","cited_by_count":8,"area":null},{"id":"2210.13388","title":"Focused Concatenation for Context-Aware Neural Machine Translation","created":"2022-10-24","cited_by_count":7,"area":null},{"id":"2104.08444","title":"Three-level Hierarchical Transformer Networks for Long-sequence and Multiple Clinical Documents Classification","created":"2021-04-17","cited_by_count":6,"area":null},{"id":"2106.11514","title":"Rethinking Adam: A Twofold Exponential Moving Average Approach","created":"2021-06-22","cited_by_count":6,"area":null},{"id":"2302.06459","title":"Encoding Sentence Position in Context-Aware Neural Machine Translation with Concatenation","created":"2023-02-13","cited_by_count":6,"area":null},{"id":"2307.00631","title":"Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers","created":"2023-07-02","cited_by_count":6,"area":null},{"id":"2207.03481","title":"Training Transformers Together","created":"2022-07-07","cited_by_count":5,"area":null},{"id":"2209.09735","title":"Relaxed Attention for Transformer Models","created":"2022-09-20","cited_by_count":5,"area":null},{"id":"2304.11249","title":"eWaSR -- an embedded-compute-ready maritime obstacle detection network","created":"2023-04-21","cited_by_count":5,"area":null},{"id":"2308.08669","title":"SkinDistilViT: Lightweight Vision Transformer for Skin Lesion Classification","created":"2023-08-16","cited_by_count":5,"area":null},{"id":"2410.21013","title":"Frequency matters: Modeling irregular morphological patterns in Spanish with Transformers","created":"2024-10-28","cited_by_count":5,"area":null},{"id":"2510.09904","title":"Stability of Transformers under Layer Normalization","created":"2025-10-10","cited_by_count":5,"area":null},{"id":"2205.00832","title":"Gradient Descent, Stochastic Optimization, and Other Tales","created":"2022-05-02","cited_by_count":4,"area":null},{"id":"2407.03076","title":"A Case Study on Context-Aware Neural Machine Translation with Multi-Task Learning","created":"2024-07-03","cited_by_count":4,"area":null},{"id":"2407.19299","title":"The Impact of LoRA Adapters on LLMs for Clinical Text Classification Under Computational and Data Constraints","created":"2024-07-27","cited_by_count":4,"area":null},{"id":"2109.13984","title":"Text Simplification for Comprehension-based Question-Answering","created":"2021-09-28","cited_by_count":3,"area":null},{"id":"2212.01140","title":"Tackling Low-Resourced Sign Language Translation: UPC at WMT-SLT 22","created":"2022-12-02","cited_by_count":3,"area":null},{"id":"2302.00954","title":"Curriculum-guided Abstractive Summarization for Mental Health Online Posts","created":"2023-02-02","cited_by_count":3,"area":null},{"id":"2302.07845","title":"NL2CMD: An Updated Workflow for Natural Language to Bash Commands Translation","created":"2023-02-15","cited_by_count":3,"area":null},{"id":"2303.12892","title":"Improving Transformer Performance for French Clinical Notes Classification Using Mixture of Experts on a Limited Dataset","created":"2023-03-22","cited_by_count":3,"area":"moe"},{"id":"2304.07877","title":"A Neural Network Transformer Model for Composite Microstructure Homogenization","created":"2023-04-16","cited_by_count":3,"area":null},{"id":"2406.09723","title":"When Will Gradient Regularization Be Harmful?","created":"2024-06-14","cited_by_count":3,"area":null},{"id":"2108.12275","title":"Can the Transformer Be Used as a Drop-in Replacement for RNNs in Text-Generating GANs?","created":"2021-08-26","cited_by_count":2,"area":null},{"id":"2203.10579","title":"Small Batch Sizes Improve Training of Low-Resource Neural MT","created":"2022-03-20","cited_by_count":2,"area":null},{"id":"2305.17633","title":"DPFormer: Learning Differentially Private Transformer on Long-Tailed Data","created":"2023-05-28","cited_by_count":2,"area":null},{"id":"2101.12640","title":"Enhancing the Transformer Decoder with Transition-based Syntax","created":"2021-01-29","cited_by_count":1,"area":null},{"id":"2104.10661","title":"Towards Automated Psychotherapy via Language Modeling","created":"2021-04-05","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":"2304.02186","title":"Training Strategies for Vision Transformers for Object Detection","created":"2023-04-05","cited_by_count":1,"area":null},{"id":"2308.06063","title":"A Case Study on Context Encoding in Multi-Encoder based Document-Level Neural Machine Translation","created":"2023-08-11","cited_by_count":1,"area":null},{"id":"2312.15872","title":"Heterogeneous Encoders Scaling In The Transformer For Neural Machine Translation","created":"2023-12-26","cited_by_count":1,"area":null},{"id":"2401.01013","title":"A Novel Transformer-Based Self-Supervised Learning Method to Enhance Photoplethysmogram Signal Artifact Detection","created":"2024-01-02","cited_by_count":1,"area":null},{"id":"2403.02609","title":"Search Intenion Network for Personalized Query Auto-Completion in E-Commerce","created":"2024-03-05","cited_by_count":1,"area":null},{"id":"2407.17716","title":"Describe Where You Are: Improving Noise-Robustness for Speech Emotion Recognition with Text Description of the Environment","created":"2024-07-25","cited_by_count":1,"area":null},{"id":"2501.01394","title":"A Unified Hyperparameter Optimization Pipeline for Transformer-Based Time Series Forecasting Models","created":"2025-01-02","cited_by_count":1,"area":null},{"id":"2503.11426","title":"Text Compression for Efficient Language Generation","created":"2025-03-14","cited_by_count":1,"area":null},{"id":"2505.13196","title":"A Physics-Inspired Optimizer: Velocity Regularized Adam","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2505.23420","title":"The Warmup Dilemma: How Learning Rate Strategies Impact Speech-to-Text Model Convergence","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2509.18690","title":"Advances in Large Language Models for Medicine","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2601.22095","title":"GeoNorm: Unify Pre-Norm and Post-Norm with Geodesic Optimization","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2105.07222","title":"On the Distributional Properties of Adaptive Gradients","created":"2021-05-15","cited_by_count":0,"area":null},{"id":"2108.01812","title":"Improving Distinction between ASR Errors and Speech Disfluencies with Feature Space Interpolation","created":"2021-08-04","cited_by_count":0,"area":null},{"id":"2109.01558","title":"Learning Neural Models for Natural Language Processing in the Face of Distributional Shift","created":"2021-09-03","cited_by_count":0,"area":null},{"id":"2209.04041","title":"Multilingual Transformer Language Model for Speech Recognition in Low-resource Languages","created":"2022-09-08","cited_by_count":0,"area":null},{"id":"2210.17079","title":"FusionFormer: Fusing Operations in Transformer for Efficient Streaming Speech Recognition","created":"2022-10-31","cited_by_count":0,"area":null},{"id":"2302.01342","title":"Curriculum-Guided Abstractive Summarization","created":"2023-02-02","cited_by_count":0,"area":null},{"id":"2305.03835","title":"Spatiotemporal Transformer for Stock Movement Prediction","created":"2023-05-05","cited_by_count":0,"area":null},{"id":"2306.03415","title":"Efficient and Interpretable Compressive Text Summarisation with Unsupervised Dual-Agent Reinforcement Learning","created":"2023-06-06","cited_by_count":0,"area":null},{"id":"2308.02870","title":"ApproBiVT: Lead ASR Models to Generalize Better Using Approximated Bias-Variance Tradeoff Guided Early Stopping and Checkpoint Averaging","created":"2023-08-05","cited_by_count":0,"area":null},{"id":"2309.13170","title":"Investigating Efficient Deep Learning Architectures For Side-Channel Attacks on AES","created":"2023-09-22","cited_by_count":0,"area":null},{"id":"2310.05350","title":"Scaling Studies for Efficient Parameter Search and Parallelism for Large Language Model Pre-training","created":"2023-10-09","cited_by_count":0,"area":null},{"id":"2311.15964","title":"Efficient Pre-training for Localized Instruction Generation of Videos","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2405.13692","title":"Challenging Gradient Boosted Decision Trees with Tabular Transformers for Fraud Detection at Booking.com","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2410.16302","title":"Computational design of target-specific linear peptide binders with TransformerBeta","created":"2024-10-07","cited_by_count":0,"area":null},{"id":"2411.00233","title":"SambaMixer: State of Health Prediction of Li-ion Batteries using Mamba State Space Models","created":"2024-10-31","cited_by_count":0,"area":"ssm"},{"id":"2411.11116","title":"DBF-Net: A Dual-Branch Network with Feature Fusion for Ultrasound Image Segmentation","created":"2024-11-17","cited_by_count":0,"area":null},{"id":"2503.04996","title":"HieroLM: Egyptian Hieroglyph Recovery with Next Word Prediction Language Model","created":"2025-03-06","cited_by_count":0,"area":null}],"next_cursor":null}