{"total":102,"rows":[{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968,"area":null},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620,"area":null},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339,"area":null},{"id":"2309.07430","title":"Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization","created":"2023-09-14","cited_by_count":246,"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":"2402.16788","title":"Why Transformers Need Adam: A Hessian Perspective","created":"2024-02-26","cited_by_count":124,"area":null},{"id":"2106.02584","title":"Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning","created":"2021-06-04","cited_by_count":113,"area":null},{"id":"2109.07740","title":"Scaling Laws for Neural Machine Translation","created":"2021-09-16","cited_by_count":111,"area":null},{"id":"2203.07852","title":"Block-Recurrent Transformers","created":"2022-03-11","cited_by_count":110,"area":null},{"id":"2105.11115","title":"Self-Attention Networks Can Process Bounded Hierarchical Languages","created":"2021-05-24","cited_by_count":105,"area":null},{"id":"2110.03742","title":"Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference","created":"2021-09-24","cited_by_count":96,"area":"moe"},{"id":"2207.02971","title":"Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding","created":"2022-07-06","cited_by_count":91,"area":null},{"id":"2106.05968","title":"Space-time Mixing Attention for Video Transformer","created":"2021-06-10","cited_by_count":84,"area":null},{"id":"2106.14343","title":"High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails","created":"2021-06-28","cited_by_count":80,"area":null},{"id":"2205.03983","title":"Building Machine Translation Systems for the Next Thousand Languages","created":"2022-05-09","cited_by_count":69,"area":null},{"id":"2105.13926","title":"Geometric Deep Learning and Equivariant Neural Networks","created":"2021-05-28","cited_by_count":65,"area":null},{"id":"2107.05768","title":"Combiner: Full Attention Transformer with Sparse Computation Cost","created":"2021-07-12","cited_by_count":64,"area":null},{"id":"2310.12487","title":"Improved Operator Learning by Orthogonal Attention","created":"2023-10-19","cited_by_count":61,"area":null},{"id":"2306.13596","title":"Max-Margin Token Selection in Attention Mechanism","created":"2023-06-23","cited_by_count":58,"area":null},{"id":"2202.01994","title":"Data Scaling Laws in NMT: The Effect of Noise and Architecture","created":"2022-02-04","cited_by_count":55,"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":"2101.00234","title":"Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers","created":"2021-01-01","cited_by_count":43,"area":null},{"id":"2203.07586","title":"Long Document Summarization with Top-down and Bottom-up Inference","created":"2022-03-15","cited_by_count":42,"area":null},{"id":"2203.08737","title":"Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey","created":"2022-03-16","cited_by_count":39,"area":null},{"id":"2105.08399","title":"Relative Positional Encoding for Transformers with Linear Complexity","created":"2021-05-18","cited_by_count":37,"area":null},{"id":"2209.05227","title":"DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization","created":"2022-09-12","cited_by_count":35,"area":null},{"id":"2308.12241","title":"LLMRec: Benchmarking Large Language Models on Recommendation Task","created":"2023-08-23","cited_by_count":30,"area":null},{"id":"2110.10030","title":"Accelerating Framework of Transformer by Hardware Design and Model Compression Co-Optimization","created":"2021-10-19","cited_by_count":27,"area":null},{"id":"2306.04226","title":"Normalization Layers Are All That Sharpness-Aware Minimization Needs","created":"2023-06-07","cited_by_count":27,"area":null},{"id":"2202.00528","title":"Examining Scaling and Transfer of Language Model Architectures for Machine Translation","created":"2022-02-01","cited_by_count":26,"area":null},{"id":"2107.00606","title":"Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition","created":"2021-07-01","cited_by_count":24,"area":null},{"id":"1905.02780","title":"Uncertainty-Aware Data Aggregation for Deep Imitation Learning","created":"2019-05-07","cited_by_count":20,"area":"offlinerl"},{"id":"2201.03110","title":"Towards the Next 1000 Languages in Multilingual Machine Translation: Exploring the Synergy Between Supervised and Self-Supervised Learning","created":"2022-01-09","cited_by_count":19,"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":"2106.09650","title":"Multi-head or Single-head? An Empirical Comparison for Transformer Training","created":"2021-06-17","cited_by_count":16,"area":null},{"id":"2302.08079","title":"Document Flattening: Beyond Concatenating Context for Document-Level Neural Machine Translation","created":"2023-02-16","cited_by_count":15,"area":null},{"id":"2106.04279","title":"Staircase Attention for Recurrent Processing of Sequences","created":"2021-06-08","cited_by_count":14,"area":null},{"id":"2106.03717","title":"Diverse Pretrained Context Encodings Improve Document Translation","created":"2021-06-07","cited_by_count":13,"area":null},{"id":"2205.02805","title":"An Empirical Study on Activity Recognition in Long Surgical Videos","created":"2022-05-05","cited_by_count":13,"area":null},{"id":"2503.01980","title":"Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval","created":"2025-03-03","cited_by_count":13,"area":"mllm"},{"id":"2310.08837","title":"Static Code Analysis in the AI Era: An In-depth Exploration of the Concept, Function, and Potential of Intelligent Code Analysis Agents","created":"2023-10-13","cited_by_count":12,"area":"agents"},{"id":"2205.10195","title":"Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration","created":"2022-05-20","cited_by_count":11,"area":null},{"id":"2308.01831","title":"Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation","created":"2023-08-03","cited_by_count":11,"area":null},{"id":"2311.13541","title":"Linear Log-Normal Attention with Unbiased Concentration","created":"2023-11-22","cited_by_count":11,"area":null},{"id":"2101.00542","title":"An Efficient Transformer Decoder with Compressed Sub-layers","created":"2021-01-03","cited_by_count":10,"area":null},{"id":"2109.06679","title":"Efficient Inference for Multilingual Neural Machine Translation","created":"2021-09-14","cited_by_count":10,"area":null},{"id":"2207.14467","title":"GTrans: Grouping and Fusing Transformer Layers for Neural Machine Translation","created":"2022-07-29","cited_by_count":10,"area":null},{"id":"2104.07829","title":"A Masked Segmental Language Model for Unsupervised Natural Language Segmentation","created":"2021-04-16","cited_by_count":9,"area":null},{"id":"2302.01128","title":"Mnemosyne: Learning to Train Transformers with Transformers","created":"2023-02-02","cited_by_count":9,"area":null},{"id":"2408.06832","title":"FlatFusion: Delving into Details of Sparse Transformer-based Camera-LiDAR Fusion for Autonomous Driving","created":"2024-08-13","cited_by_count":9,"area":null},{"id":"2105.07071","title":"Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End","created":"2021-05-14","cited_by_count":8,"area":null},{"id":"2205.08119","title":"ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks","created":"2022-05-17","cited_by_count":8,"area":null},{"id":"2504.04702","title":"Provable Failure of Language Models in Learning Majority Boolean Logic via Gradient Descent","created":"2025-04-07","cited_by_count":8,"area":"lr"},{"id":"2203.07627","title":"Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translation","created":"2022-03-15","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":"2407.00416","title":"Too Late to Train, Too Early To Use? A Study on Necessity and Viability of Low-Resource Bengali LLMs","created":"2024-06-29","cited_by_count":7,"area":null},{"id":"2304.07210","title":"Measuring Re-identification Risk","created":"2023-04-12","cited_by_count":6,"area":null},{"id":"2102.06856","title":"Generating Diversified Comments via Reader-Aware Topic Modeling and Saliency Detection","created":"2021-02-13","cited_by_count":5,"area":null},{"id":"2105.12523","title":"Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation","created":"2021-05-26","cited_by_count":5,"area":null},{"id":"2208.06061","title":"Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages","created":"2022-08-11","cited_by_count":5,"area":null},{"id":"2212.11791","title":"Training Integer-Only Deep Recurrent Neural Networks","created":"2022-12-22","cited_by_count":5,"area":null},{"id":"2205.11588","title":"Simple Recurrence Improves Masked Language Models","created":"2022-05-23","cited_by_count":4,"area":null},{"id":"2212.04205","title":"DC-MBR: Distributional Cooling for Minimum Bayesian Risk Decoding","created":"2022-12-08","cited_by_count":4,"area":null},{"id":"2212.07877","title":"Manifestations of Xenophobia in AI Systems","created":"2022-12-15","cited_by_count":4,"area":null},{"id":"2109.09828","title":"iRNN: Integer-only Recurrent Neural Network","created":"2021-09-20","cited_by_count":3,"area":null},{"id":"2201.12854","title":"Fast Monte-Carlo Approximation of the Attention Mechanism","created":"2022-01-30","cited_by_count":3,"area":null},{"id":"2210.08431","title":"Modeling Context With Linear Attention for Scalable Document-Level Translation","created":"2022-10-16","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":"2305.07034","title":"Quran Recitation Recognition using End-to-End Deep Learning","created":"2023-05-10","cited_by_count":3,"area":null},{"id":"2509.08897","title":"Recurrence Meets Transformers for Universal Multimodal Retrieval","created":"2025-09-10","cited_by_count":3,"area":"mllm"},{"id":"2106.06183","title":"Improving RNN-T ASR Performance with Date-Time and Location Awareness","created":"2021-06-11","cited_by_count":2,"area":null},{"id":"2108.10197","title":"Deploying a BERT-based Query-Title Relevance Classifier in a Production System: a View from the Trenches","created":"2021-08-23","cited_by_count":2,"area":null},{"id":"2110.13229","title":"Distributionally Robust Recurrent Decoders with Random Network Distillation","created":"2021-10-25","cited_by_count":2,"area":null},{"id":"2201.02009","title":"PAEG: Phrase-level Adversarial Example Generation for Neural Machine Translation","created":"2022-01-06","cited_by_count":2,"area":null},{"id":"2205.00659","title":"The Implicit Length Bias of Label Smoothing on Beam Search Decoding","created":"2022-05-02","cited_by_count":2,"area":null},{"id":"2207.03327","title":"Exploring the sequence length bottleneck in the Transformer for Image Captioning","created":"2022-07-07","cited_by_count":2,"area":null},{"id":"2309.04734","title":"Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering","created":"2023-09-09","cited_by_count":2,"area":null},{"id":"2312.09402","title":"CERN for AI: A Theoretical Framework for Autonomous Simulation-Based Artificial Intelligence Testing and Alignment","created":"2023-12-14","cited_by_count":2,"area":null},{"id":"2401.10747","title":"Multimodal Sentiment Analysis with Missing Modality: A Knowledge-Transfer Approach","created":"2023-12-28","cited_by_count":2,"area":null},{"id":"2107.04512","title":"Using Machine Translation to Localize Task Oriented NLG Output","created":"2021-07-09","cited_by_count":1,"area":null},{"id":"2203.15860","title":"Visualizing the Relationship Between Encoded Linguistic Information and Task Performance","created":"2022-03-29","cited_by_count":1,"area":null},{"id":"2208.11108","title":"Efficient Attention-free Video Shift Transformers","created":"2022-08-23","cited_by_count":1,"area":null},{"id":"2209.12714","title":"Text Summarization with Oracle Expectation","created":"2022-09-26","cited_by_count":1,"area":null},{"id":"2211.13899","title":"Comparison Study Between Token Classification and Sequence Classification In Text Classification","created":"2022-11-25","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":"2103.03108","title":"An empirical analysis of phrase-based and neural machine translation","created":"2021-03-04","cited_by_count":0,"area":null},{"id":"2103.12838","title":"Repairing Pronouns in Translation with BERT-Based Post-Editing","created":"2021-03-23","cited_by_count":0,"area":null},{"id":"2104.08388","title":"Neural String Edit Distance","created":"2021-04-16","cited_by_count":0,"area":null},{"id":"2109.13673","title":"Nana-HDR: A Non-attentive Non-autoregressive Hybrid Model for TTS","created":"2021-09-28","cited_by_count":0,"area":null},{"id":"2111.03813","title":"Analyzing Architectures for Neural Machine Translation Using Low Computational Resources","created":"2021-11-06","cited_by_count":0,"area":null},{"id":"2203.16149","title":"Tampered VAE for Improved Satellite Image Time Series Classification","created":"2022-03-30","cited_by_count":0,"area":null},{"id":"2211.03237","title":"Parallel Attention Forcing for Machine Translation","created":"2022-11-06","cited_by_count":0,"area":null},{"id":"2310.07091","title":"Jaeger: A Concatenation-Based Multi-Transformer VQA Model","created":"2023-10-11","cited_by_count":0,"area":null},{"id":"2310.14561","title":"F$^2$AT: Feature-Focusing Adversarial Training via Disentanglement of Natural and Perturbed Patterns","created":"2023-10-23","cited_by_count":0,"area":null},{"id":"2310.14659","title":"Predicting Accurate Lagrangian Multipliers for Mixed Integer Linear Programs","created":"2023-10-23","cited_by_count":0,"area":null},{"id":"2404.07792","title":"Nostra Domina at EvaLatin 2024: Improving Latin Polarity Detection through Data Augmentation","created":"2024-04-11","cited_by_count":0,"area":null},{"id":"2408.04723","title":"Survey: Transformer-based Models in Data Modality Conversion","created":"2024-08-08","cited_by_count":0,"area":null},{"id":"2408.05391","title":"SAMSA: Efficient Transformer for Many Data Modalities","created":"2024-08-10","cited_by_count":0,"area":null},{"id":"2411.03375","title":"Kernel Approximation using Analog In-Memory Computing","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2504.17252","title":"Low-Resource Neural Machine Translation Using Recurrent Neural Networks and Transfer Learning: A Case Study on English-to-Igbo","created":"2025-04-24","cited_by_count":0,"area":null}],"next_cursor":"100"}