{"total":76,"rows":[{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780,"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":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403,"area":null},{"id":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154,"area":null},{"id":"2105.03482","title":"Measuring and Increasing Context Usage in Context-Aware Machine Translation","created":"2021-05-07","cited_by_count":48,"area":null},{"id":"2405.14394","title":"Instruction Tuning With Loss Over Instructions","created":"2024-05-23","cited_by_count":40,"area":null},{"id":"2101.01761","title":"AutoDropout: Learning Dropout Patterns to Regularize Deep Networks","created":"2021-01-05","cited_by_count":35,"area":null},{"id":"2103.07552","title":"Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning","created":"2021-03-12","cited_by_count":35,"area":null},{"id":"2108.01887","title":"PARADISE: Exploiting Parallel Data for Multilingual Sequence-to-Sequence Pretraining","created":"2021-08-04","cited_by_count":21,"area":null},{"id":"2103.08827","title":"Semi-Supervised Graph-to-Graph Translation","created":"2021-03-16","cited_by_count":18,"area":null},{"id":"2410.03735","title":"Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling","created":"2024-09-30","cited_by_count":18,"area":null},{"id":"2401.08350","title":"Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models","created":"2024-01-16","cited_by_count":17,"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":"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":"2110.01811","title":"On the Complementarity between Pre-Training and Back-Translation for Neural Machine Translation","created":"2021-10-05","cited_by_count":14,"area":null},{"id":"2208.08110","title":"PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentation","created":"2022-08-17","cited_by_count":14,"area":null},{"id":"2304.13539","title":"Tensor Decomposition for Model Reduction in Neural Networks: A Review","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2105.02692","title":"Learning to Perturb Word Embeddings for Out-of-distribution QA","created":"2021-05-06","cited_by_count":13,"area":null},{"id":"2110.07166","title":"CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization","created":"2021-10-14","cited_by_count":11,"area":null},{"id":"2109.03402","title":"Mixup Decoding for Diverse Machine Translation","created":"2021-09-08","cited_by_count":10,"area":null},{"id":"2104.07284","title":"Consistency Training with Virtual Adversarial Discrete Perturbation","created":"2021-04-15","cited_by_count":9,"area":null},{"id":"2105.14210","title":"Exploiting Position Bias for Robust Aspect Sentiment Classification","created":"2021-05-29","cited_by_count":9,"area":null},{"id":"2204.00665","title":"CipherDAug: Ciphertext based Data Augmentation for Neural Machine Translation","created":"2022-04-01","cited_by_count":9,"area":null},{"id":"2205.10068","title":"Understanding and Mitigating the Uncertainty in Zero-Shot Translation","created":"2022-05-20","cited_by_count":9,"area":null},{"id":"2408.05086","title":"A systematic framework for generating novel experimental hypotheses from language models","created":"2024-08-09","cited_by_count":9,"area":null},{"id":"2101.05469","title":"Text Augmentation in a Multi-Task View","created":"2021-01-14","cited_by_count":8,"area":null},{"id":"2109.03645","title":"Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach","created":"2021-09-08","cited_by_count":8,"area":null},{"id":"2402.10516","title":"Generative AI for Controllable Protein Sequence Design: A Survey","created":"2024-02-16","cited_by_count":8,"area":null},{"id":"2409.18893","title":"HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models","created":"2024-09-27","cited_by_count":8,"area":null},{"id":"2310.16681","title":"BabyStories: Can Reinforcement Learning Teach Baby Language Models to Write Better Stories?","created":"2023-10-25","cited_by_count":7,"area":"alignment"},{"id":"2508.16100","title":"CYCLE-INSTRUCT: Fully Seed-Free Instruction Tuning via Dual Self-Training and Cycle Consistency","created":"2025-08-22","cited_by_count":6,"area":"alignment"},{"id":"2103.03457","title":"IOT: Instance-wise Layer Reordering for Transformer Structures","created":"2021-03-05","cited_by_count":5,"area":null},{"id":"2104.08384","title":"\"Wikily\" Supervised Neural Translation Tailored to Cross-Lingual Tasks","created":"2021-04-16","cited_by_count":5,"area":null},{"id":"2109.05602","title":"Good-Enough Example Extrapolation","created":"2021-09-12","cited_by_count":5,"area":null},{"id":"2206.00794","title":"Sequential Bayesian Neural Subnetwork Ensembles","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2210.12653","title":"SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training","created":"2022-10-23","cited_by_count":5,"area":null},{"id":"2305.18240","title":"XGrad: Boosting Gradient-Based Optimizers With Weight Prediction","created":"2023-05-26","cited_by_count":5,"area":null},{"id":"2307.05779","title":"Neural Machine Translation Data Generation and Augmentation using ChatGPT","created":"2023-07-11","cited_by_count":5,"area":null},{"id":"2507.09834","title":"Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction","created":"2025-07-14","cited_by_count":5,"area":null},{"id":"2103.11088","title":"Token-wise Curriculum Learning for Neural Machine Translation","created":"2021-03-20","cited_by_count":4,"area":null},{"id":"2111.03294","title":"A Syntax-Guided Grammatical Error Correction Model with Dependency Tree Correction","created":"2021-11-05","cited_by_count":4,"area":null},{"id":"2204.02027","title":"A Survey on Dropout Methods and Experimental Verification in Recommendation","created":"2022-04-05","cited_by_count":4,"area":null},{"id":"2204.12225","title":"Flow-Adapter Architecture for Unsupervised Machine Translation","created":"2022-04-26","cited_by_count":4,"area":null},{"id":"2212.09670","title":"StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer","created":"2022-12-19","cited_by_count":4,"area":null},{"id":"2312.00839","title":"PipeOptim: Ensuring Effective 1F1B Schedule with Optimizer-Dependent Weight Prediction","created":"2023-12-01","cited_by_count":4,"area":null},{"id":"2401.15360","title":"Importance-Aware Data Augmentation for Document-Level Neural Machine Translation","created":"2024-01-27","cited_by_count":4,"area":null},{"id":"2110.15149","title":"Diversity-Driven Combination for Grammatical Error Correction","created":"2021-10-28","cited_by_count":3,"area":null},{"id":"2302.08659","title":"Uncertainty-aware Self-training for Low-resource Neural Sequence Labeling","created":"2023-02-17","cited_by_count":3,"area":null},{"id":"2403.03575","title":"gaHealth: An English-Irish Bilingual Corpus of Health Data","created":"2024-03-06","cited_by_count":3,"area":null},{"id":"2502.21265","title":"Token-level Ensembling of Models with Different Vocabularies","created":"2025-02-28","cited_by_count":3,"area":null},{"id":"2109.12296","title":"Jointly Learning to Repair Code and Generate Commit Message","created":"2021-09-25","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":"2403.02367","title":"adaptNMT: an open-source, language-agnostic development environment for Neural Machine Translation","created":"2024-03-04","cited_by_count":2,"area":null},{"id":"2603.19931","title":"SAGE: Sustainable Agent-Guided Expert-tuning for Culturally Attuned Translation in Low-Resource Southeast Asia","created":"2026-03-20","cited_by_count":2,"area":"agents"},{"id":"2204.12165","title":"When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?","created":"2022-04-26","cited_by_count":1,"area":null},{"id":"2207.04399","title":"Horizontal and Vertical Attention in Transformers","created":"2022-07-10","cited_by_count":1,"area":null},{"id":"2212.10197","title":"EIT: Enhanced Interactive Transformer","created":"2022-12-20","cited_by_count":1,"area":null},{"id":"2305.03207","title":"Investigating Lexical Sharing in Multilingual Machine Translation for Indian Languages","created":"2023-05-04","cited_by_count":1,"area":null},{"id":"2305.05214","title":"CharSpan: Utilizing Lexical Similarity to Enable Zero-Shot Machine Translation for Extremely Low-resource Languages","created":"2023-05-09","cited_by_count":1,"area":null},{"id":"2305.13000","title":"Bidirectional Transformer Reranker for Grammatical Error Correction","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2307.12835","title":"Joint Dropout: Improving Generalizability in Low-Resource Neural Machine Translation through Phrase Pair Variables","created":"2023-07-24","cited_by_count":1,"area":null},{"id":"2307.16400","title":"SelfSeg: A Self-supervised Sub-word Segmentation Method for Neural Machine Translation","created":"2023-07-31","cited_by_count":1,"area":null},{"id":"2403.00144","title":"EBBS: An Ensemble with Bi-Level Beam Search for Zero-Shot Machine Translation","created":"2024-02-29","cited_by_count":1,"area":null},{"id":"2404.05943","title":"Interplay of Machine Translation, Diacritics, and Diacritization","created":"2024-04-09","cited_by_count":1,"area":null},{"id":"2510.18321","title":"Beyond Single Models: Mitigating Multimodal Hallucinations via Adaptive Token Ensemble Decoding","created":"2025-10-21","cited_by_count":1,"area":"mllm"},{"id":"2601.11002","title":"Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2112.10543","title":"Spiral Language Modeling","created":"2021-12-20","cited_by_count":0,"area":null},{"id":"2311.09505","title":"SegMix: A Simple Structure-Aware Data Augmentation Method","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2401.16078","title":"Understanding the effects of word-level linguistic annotations in under-resourced neural machine translation","created":"2024-01-29","cited_by_count":0,"area":null},{"id":"2401.16086","title":"Non-Fluent Synthetic Target-Language Data Improve Neural Machine Translation","created":"2024-01-29","cited_by_count":0,"area":null},{"id":"2406.02517","title":"Deterministic Reversible Data Augmentation for Neural Machine Translation","created":"2024-06-04","cited_by_count":0,"area":null},{"id":"2509.07471","title":"From Scarcity to Efficiency: Investigating the Effects of Data Augmentation on African Machine Translation","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2509.21801","title":"Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2601.19124","title":"Leveraging Sentence-oriented Augmentation and Transformer-Based Architecture for Vietnamese-Bahnaric Translation","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2609.06025","title":"Factors Influencing the Emergence of Dependency Length Minimization in Neural Agent Simulations","created":"2026-09-05","cited_by_count":0,"area":null}],"next_cursor":null}