{"total":193,"rows":[{"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":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103,"area":null},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"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":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502,"area":null},{"id":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403,"area":null},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400,"area":null},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354,"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":"2102.10662","title":"Medical Transformer: Gated Axial-Attention for Medical Image Segmentation","created":"2021-02-21","cited_by_count":320,"area":null},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242,"area":null},{"id":"2106.14448","title":"R-Drop: Regularized Dropout for Neural Networks","created":"2021-06-28","cited_by_count":202,"area":null},{"id":"2110.03675","title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis","created":"2021-10-07","cited_by_count":200,"area":null},{"id":"2106.06639","title":"Federated Learning with Buffered Asynchronous Aggregation","created":"2021-06-11","cited_by_count":190,"area":null},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182,"area":null},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179,"area":null},{"id":"2407.18921","title":"Mobile Edge Intelligence for Large Language Models: A Contemporary Survey","created":"2024-07-09","cited_by_count":128,"area":null},{"id":"2104.12836","title":"Multimodal Contrastive Training for Visual Representation Learning","created":"2021-04-26","cited_by_count":124,"area":null},{"id":"2104.14690","title":"Entailment as Few-Shot Learner","created":"2021-04-29","cited_by_count":123,"area":null},{"id":"2103.11943","title":"BERT: A Review of Applications in Natural Language Processing and Understanding","created":"2021-03-22","cited_by_count":109,"area":null},{"id":"2111.09388","title":"High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics","created":"2021-11-17","cited_by_count":104,"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":"2106.04632","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","created":"2021-06-08","cited_by_count":95,"area":null},{"id":"2104.06022","title":"Lessons on Parameter Sharing across Layers in Transformers","created":"2021-04-13","cited_by_count":85,"area":null},{"id":"2104.07705","title":"How to Train BERT with an Academic Budget","created":"2021-04-15","cited_by_count":80,"area":null},{"id":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73,"area":null},{"id":"2202.08625","title":"Revisiting Over-smoothing in BERT from the Perspective of Graph","created":"2022-02-17","cited_by_count":72,"area":null},{"id":"2106.09898","title":"Bad Characters: Imperceptible NLP Attacks","created":"2021-06-18","cited_by_count":71,"area":null},{"id":"2104.02724","title":"Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions","created":"2021-04-06","cited_by_count":61,"area":null},{"id":"2108.05885","title":"The paradox of the compositionality of natural language: a neural machine translation case study","created":"2021-08-12","cited_by_count":59,"area":null},{"id":"2301.11913","title":"SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient","created":"2023-01-27","cited_by_count":59,"area":null},{"id":"2106.10207","title":"Distributed Deep Learning in Open Collaborations","created":"2021-06-18","cited_by_count":58,"area":null},{"id":"2112.01683","title":"TransZero: Attribute-guided Transformer for Zero-Shot Learning","created":"2021-12-03","cited_by_count":54,"area":null},{"id":"2312.16903","title":"Spike No More: Stabilizing the Pre-training of Large Language Models","created":"2023-12-28","cited_by_count":52,"area":null},{"id":"2102.12871","title":"SparseBERT: Rethinking the Importance Analysis in Self-attention","created":"2021-02-25","cited_by_count":46,"area":null},{"id":"2110.04590","title":"An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition","created":"2021-10-09","cited_by_count":39,"area":null},{"id":"2109.05644","title":"SHAPE: Shifted Absolute Position Embedding for Transformers","created":"2021-09-13","cited_by_count":37,"area":null},{"id":"2109.04588","title":"BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation","created":"2021-09-09","cited_by_count":35,"area":null},{"id":"2402.16705","title":"SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection","created":"2024-02-26","cited_by_count":34,"area":null},{"id":"2108.05307","title":"Video Transformer for Deepfake Detection with Incremental Learning","created":"2021-08-11","cited_by_count":33,"area":null},{"id":"2212.11696","title":"Reversible Column Networks","created":"2022-12-22","cited_by_count":32,"area":null},{"id":"2102.07594","title":"Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT","created":"2021-02-15","cited_by_count":31,"area":null},{"id":"2204.04667","title":"Linear Complexity Randomized Self-attention Mechanism","created":"2022-04-10","cited_by_count":31,"area":null},{"id":"2103.13597","title":"Mask Attention Networks: Rethinking and Strengthen Transformer","created":"2021-03-25","cited_by_count":28,"area":null},{"id":"2112.08643","title":"TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning","created":"2021-12-16","cited_by_count":28,"area":null},{"id":"2109.04715","title":"AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languages","created":"2021-09-10","cited_by_count":24,"area":null},{"id":"2103.01075","title":"OmniNet: Omnidirectional Representations from Transformers","created":"2021-03-01","cited_by_count":23,"area":null},{"id":"2302.04542","title":"Efficient Attention via Control Variates","created":"2023-02-09","cited_by_count":23,"area":null},{"id":"2104.11125","title":"ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training","created":"2021-04-21","cited_by_count":22,"area":null},{"id":"2110.10472","title":"Multilingual Unsupervised Neural Machine Translation with Denoising Adapters","created":"2021-10-20","cited_by_count":22,"area":null},{"id":"2110.09574","title":"Multilingual Domain Adaptation for NMT: Decoupling Language and Domain Information with Adapters","created":"2021-10-18","cited_by_count":21,"area":null},{"id":"2202.07959","title":"EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation","created":"2022-02-16","cited_by_count":21,"area":null},{"id":"2305.02424","title":"Backdoor Learning on Sequence to Sequence Models","created":"2023-05-03","cited_by_count":21,"area":null},{"id":"2106.03146","title":"Oriented Object Detection with Transformer","created":"2021-06-06","cited_by_count":20,"area":null},{"id":"2204.09151","title":"Multi-Camera Multiple 3D Object Tracking on the Move for Autonomous Vehicles","created":"2022-04-19","cited_by_count":20,"area":null},{"id":"2502.14801","title":"AVD2: Accident Video Diffusion for Accident Video Description","created":"2025-02-20","cited_by_count":20,"area":null},{"id":"2105.06987","title":"Scaling Ensemble Distribution Distillation to Many Classes with Proxy Targets","created":"2021-05-14","cited_by_count":19,"area":null},{"id":"2110.11299","title":"Transformer Acceleration with Dynamic Sparse Attention","created":"2021-10-21","cited_by_count":19,"area":null},{"id":"2202.02842","title":"Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data","created":"2022-02-06","cited_by_count":19,"area":null},{"id":"2205.10350","title":"Lossless Acceleration for Seq2seq Generation with Aggressive Decoding","created":"2022-05-20","cited_by_count":18,"area":null},{"id":"2104.01853","title":"Rethinking Perturbations in Encoder-Decoders for Fast Training","created":"2021-04-05","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":"2202.12607","title":"JParaCrawl v3.0: A Large-scale English-Japanese Parallel Corpus","created":"2022-02-25","cited_by_count":17,"area":null},{"id":"2106.13627","title":"Language Models are Good Translators","created":"2021-06-25","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":"2106.11891","title":"On the Evaluation of Machine Translation for Terminology Consistency","created":"2021-06-22","cited_by_count":15,"area":null},{"id":"2107.08212","title":"On the Copying Behaviors of Pre-Training for Neural Machine Translation","created":"2021-07-17","cited_by_count":15,"area":null},{"id":"2202.02664","title":"No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models","created":"2022-02-06","cited_by_count":15,"area":null},{"id":"2309.01826","title":"One Wide Feedforward is All You Need","created":"2023-09-04","cited_by_count":15,"area":null},{"id":"2407.13677","title":"PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformers","created":"2024-07-18","cited_by_count":15,"area":null},{"id":"2109.00165","title":"An Unsupervised Method for Building Sentence Simplification Corpora in Multiple Languages","created":"2021-09-01","cited_by_count":14,"area":null},{"id":"2203.00091","title":"Dynamic N:M Fine-grained Structured Sparse Attention Mechanism","created":"2022-02-28","cited_by_count":14,"area":null},{"id":"2212.06011","title":"A Neural ODE Interpretation of Transformer Layers","created":"2022-12-12","cited_by_count":14,"area":null},{"id":"2101.08942","title":"Enriching Non-Autoregressive Transformer with Syntactic and SemanticStructures for Neural Machine Translation","created":"2021-01-22","cited_by_count":13,"area":null},{"id":"2106.04718","title":"FastSeq: Make Sequence Generation Faster","created":"2021-06-08","cited_by_count":13,"area":null},{"id":"2204.06812","title":"Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation","created":"2022-04-14","cited_by_count":13,"area":null},{"id":"2206.08901","title":"SYMBA: Symbolic Computation of Squared Amplitudes in High Energy Physics with Machine Learning","created":"2022-06-17","cited_by_count":13,"area":null},{"id":"2305.02665","title":"Learning Language-Specific Layers for Multilingual Machine Translation","created":"2023-05-04","cited_by_count":13,"area":null},{"id":"2401.08088","title":"Enhancing Document-level Translation of Large Language Model via Translation Mixed-instructions","created":"2024-01-16","cited_by_count":13,"area":null},{"id":"2104.02308","title":"ODE Transformer: An Ordinary Differential Equation-Inspired Model for Neural Machine Translation","created":"2021-04-06","cited_by_count":12,"area":null},{"id":"2104.07541","title":"Reward Optimization for Neural Machine Translation with Learned Metrics","created":"2021-04-15","cited_by_count":12,"area":null},{"id":"2106.03297","title":"On the Language Coverage Bias for Neural Machine Translation","created":"2021-06-07","cited_by_count":12,"area":null},{"id":"2106.04060","title":"Self-supervised and Supervised Joint Training for Resource-rich Machine Translation","created":"2021-06-08","cited_by_count":12,"area":null},{"id":"2110.12199","title":"PhoMT: A High-Quality and Large-Scale Benchmark Dataset for Vietnamese-English Machine Translation","created":"2021-10-23","cited_by_count":12,"area":null},{"id":"2109.11034","title":"Conditional Poisson Stochastic Beam Search","created":"2021-09-22","cited_by_count":11,"area":null},{"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":"2301.09008","title":"Poor Man's Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference","created":"2023-01-21","cited_by_count":11,"area":null},{"id":"2310.14684","title":"SpEL: Structured Prediction for Entity Linking","created":"2023-10-23","cited_by_count":11,"area":null},{"id":"2105.13573","title":"Investigating Code-Mixed Modern Standard Arabic-Egyptian to English Machine Translation","created":"2021-05-28","cited_by_count":10,"area":null},{"id":"2109.03402","title":"Mixup Decoding for Diverse Machine Translation","created":"2021-09-08","cited_by_count":10,"area":null},{"id":"2112.08914","title":"Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling","created":"2021-12-16","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":"2307.08074","title":"Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling","created":"2023-07-16","cited_by_count":10,"area":null},{"id":"2204.03498","title":"On the Effectiveness of Pretrained Models for API Learning","created":"2022-04-05","cited_by_count":9,"area":null},{"id":"2206.03318","title":"LegoNN: Building Modular Encoder-Decoder Models","created":"2022-06-07","cited_by_count":9,"area":null},{"id":"2305.15718","title":"Towards Higher Pareto Frontier in Multilingual Machine Translation","created":"2023-05-25","cited_by_count":9,"area":null},{"id":"2501.14577","title":"ZETA: Leveraging Z-order Curves for Efficient Top-k Attention","created":"2025-01-24","cited_by_count":9,"area":null},{"id":"2109.04002","title":"Competence-based Curriculum Learning for Multilingual Machine Translation","created":"2021-09-09","cited_by_count":8,"area":null},{"id":"2201.05313","title":"ExtraPhrase: Efficient Data Augmentation for Abstractive Summarization","created":"2022-01-14","cited_by_count":8,"area":null}],"next_cursor":"100"}