{"total":95,"rows":[{"id":"2301.12726","title":"Specializing Smaller Language Models towards Multi-Step Reasoning","created":"2023-01-30","cited_by_count":251,"area":"lr"},{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184,"area":null},{"id":"2203.14001","title":"Knowledge Distillation with the Reused Teacher Classifier","created":"2022-03-26","cited_by_count":141,"area":"distill"},{"id":"2106.15115","title":"Neural Machine Translation for Low-Resource Languages: A Survey","created":"2021-06-29","cited_by_count":109,"area":null},{"id":"2105.09501","title":"Contrastive Learning for Many-to-many Multilingual Neural Machine Translation","created":"2021-05-20","cited_by_count":108,"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":"2009.07253","title":"Autoregressive Knowledge Distillation through Imitation Learning","created":"2020-09-15","cited_by_count":74,"area":"offlinerl"},{"id":"2103.04062","title":"Adaptive Multi-Teacher Multi-level Knowledge Distillation","created":"2021-03-06","cited_by_count":72,"area":"distill"},{"id":"2408.10189","title":"Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models","created":"2024-08-19","cited_by_count":67,"area":"ssm"},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2104.00676","title":"Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study","created":"2021-04-01","cited_by_count":51,"area":"distill"},{"id":"2105.09259","title":"Learning Language Specific Sub-network for Multilingual Machine Translation","created":"2021-05-19","cited_by_count":48,"area":null},{"id":"2105.12967","title":"Selective Knowledge Distillation for Neural Machine Translation","created":"2021-05-27","cited_by_count":43,"area":"distill"},{"id":"2112.02043","title":"Multilingual training for Software Engineering","created":"2021-12-03","cited_by_count":43,"area":null},{"id":"2104.08154","title":"Counter-Interference Adapter for Multilingual Machine Translation","created":"2021-04-16","cited_by_count":40,"area":null},{"id":"2109.02903","title":"IndicBART: A Pre-trained Model for Indic Natural Language Generation","created":"2021-09-07","cited_by_count":39,"area":null},{"id":"2105.13880","title":"Knowledge Inheritance for Pre-trained Language Models","created":"2021-05-28","cited_by_count":38,"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":"2111.02086","title":"Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task","created":"2021-11-03","cited_by_count":34,"area":null},{"id":"2105.14556","title":"Diversifying Dialog Generation via Adaptive Label Smoothing","created":"2021-05-30","cited_by_count":25,"area":null},{"id":"2406.17328","title":"Dual-Space Knowledge Distillation for Large Language Models","created":"2024-06-25","cited_by_count":25,"area":"distill"},{"id":"2210.16103","title":"Collaborative Multi-Teacher Knowledge Distillation for Learning Low Bit-width Deep Neural Networks","created":"2022-10-27","cited_by_count":23,"area":"distill"},{"id":"2112.03473","title":"Improving Neural Cross-Lingual Summarization via Employing Optimal Transport Distance for Knowledge Distillation","created":"2021-12-07","cited_by_count":22,"area":"distill"},{"id":"2312.05284","title":"SlimSAM: 0.1% Data Makes Segment Anything Slim","created":"2023-12-08","cited_by_count":20,"area":null},{"id":"2108.13873","title":"Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs","created":"2021-08-29","cited_by_count":18,"area":null},{"id":"2107.12087","title":"Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation","created":"2021-07-26","cited_by_count":17,"area":"distill"},{"id":"2110.08246","title":"Tricks for Training Sparse Translation Models","created":"2021-10-15","cited_by_count":17,"area":null},{"id":"2107.04239","title":"A Survey on Low-Resource Neural Machine Translation","created":"2021-07-09","cited_by_count":16,"area":null},{"id":"2305.11096","title":"Cross-modality Data Augmentation for End-to-End Sign Language Translation","created":"2023-05-18","cited_by_count":16,"area":null},{"id":"2106.02834","title":"MergeDistill: Merging Pre-trained Language Models using Distillation","created":"2021-06-05","cited_by_count":13,"area":null},{"id":"2404.14827","title":"Sentence-Level or Token-Level? A Comprehensive Study on Knowledge Distillation","created":"2024-04-23","cited_by_count":12,"area":"distill"},{"id":"2102.03551","title":"Jointly Improving Language Understanding and Generation with Quality-Weighted Weak Supervision of Automatic Labeling","created":"2021-02-06","cited_by_count":11,"area":null},{"id":"2105.13608","title":"Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax","created":"2021-05-28","cited_by_count":10,"area":null},{"id":"2109.05256","title":"Multilingual Translation via Grafting Pre-trained Language Models","created":"2021-09-11","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":"2205.00479","title":"Nearest Neighbor Knowledge Distillation for Neural Machine Translation","created":"2022-05-01","cited_by_count":10,"area":"distill"},{"id":"2207.04900","title":"UM4: Unified Multilingual Multiple Teacher-Student Model for Zero-Resource Neural Machine Translation","created":"2022-07-11","cited_by_count":10,"area":"distill"},{"id":"2305.08096","title":"Towards Understanding and Improving Knowledge Distillation for Neural Machine Translation","created":"2023-05-14","cited_by_count":10,"area":"distill"},{"id":"2403.09522","title":"MT-PATCHER: Selective and Extendable Knowledge Distillation from Large Language Models for Machine Translation","created":"2024-03-14","cited_by_count":10,"area":"distill"},{"id":"2408.06537","title":"Introducing the NewsPaLM MBR and QE Dataset: LLM-Generated High-Quality Parallel Data Outperforms Traditional Web-Crawled Data","created":"2024-08-13","cited_by_count":10,"area":null},{"id":"2305.14189","title":"Beyond Shared Vocabulary: Increasing Representational Word Similarities across Languages for Multilingual Machine Translation","created":"2023-05-23","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":"2407.10456","title":"Don't Throw Away Data: Better Sequence Knowledge Distillation","created":"2024-07-15","cited_by_count":9,"area":"distill"},{"id":"2109.15196","title":"Multilingual AMR Parsing with Noisy Knowledge Distillation","created":"2021-09-30","cited_by_count":8,"area":"distill"},{"id":"2504.11426","title":"A Dual-Space Framework for General Knowledge Distillation of Large Language Models","created":"2025-04-15","cited_by_count":8,"area":"distill"},{"id":"2110.06961","title":"Language Modelling via Learning to Rank","created":"2021-10-13","cited_by_count":7,"area":null},{"id":"2106.12607","title":"Dealing with training and test segmentation mismatch: FBK@IWSLT2021","created":"2021-06-23","cited_by_count":6,"area":"distill"},{"id":"2209.02030","title":"Distilling the Knowledge of BERT for CTC-based ASR","created":"2022-09-05","cited_by_count":6,"area":null},{"id":"2212.09666","title":"MultiCoder: Multi-Programming-Lingual Pre-Training for Low-Resource Code Completion","created":"2022-12-19","cited_by_count":6,"area":"moe"},{"id":"2305.14263","title":"LIMIT: Language Identification, Misidentification, and Translation using Hierarchical Models in 350+ Languages","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2203.02651","title":"Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning","created":"2022-03-05","cited_by_count":5,"area":null},{"id":"2211.03946","title":"Understanding the Role of Mixup in Knowledge Distillation: An Empirical Study","created":"2022-11-08","cited_by_count":5,"area":"distill"},{"id":"2212.02800","title":"Life-long Learning for Multilingual Neural Machine Translation with Knowledge Distillation","created":"2022-12-06","cited_by_count":5,"area":"distill"},{"id":"2304.09388","title":"An Empirical Study of Leveraging Knowledge Distillation for Compressing Multilingual Neural Machine Translation Models","created":"2023-04-19","cited_by_count":5,"area":"distill"},{"id":"2305.10384","title":"Logit-Based Ensemble Distribution Distillation for Robust Autoregressive Sequence Uncertainties","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2112.08670","title":"Amortized Noisy Channel Neural Machine Translation","created":"2021-12-16","cited_by_count":4,"area":null},{"id":"2201.07365","title":"Improving Neural Machine Translation by Denoising Training","created":"2022-01-19","cited_by_count":4,"area":null},{"id":"2202.06620","title":"What is Next when Sequential Prediction Meets Implicitly Hard Interaction?","created":"2022-02-14","cited_by_count":4,"area":null},{"id":"2304.12314","title":"Distilling from Similar Tasks for Transfer Learning on a Budget","created":"2023-04-24","cited_by_count":4,"area":null},{"id":"2310.13499","title":"DistillCSE: Distilled Contrastive Learning for Sentence Embeddings","created":"2023-10-20","cited_by_count":4,"area":"distill"},{"id":"2409.12586","title":"Efficient Knowledge Distillation: Empowering Small Language Models with Teacher Model Insights","created":"2024-09-19","cited_by_count":4,"area":"distill"},{"id":"2410.01483","title":"Foldable SuperNets: Scalable Merging of Transformers with Different Initializations and Tasks","created":"2024-10-02","cited_by_count":4,"area":null},{"id":"2504.14694","title":"Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data","created":"2025-04-20","cited_by_count":4,"area":"distill"},{"id":"2206.02252","title":"Exploring Cross-lingual Textual Style Transfer with Large Multilingual Language Models","created":"2022-06-05","cited_by_count":3,"area":null},{"id":"2102.08357","title":"Revisiting Language Encoding in Learning Multilingual Representations","created":"2021-02-16","cited_by_count":2,"area":null},{"id":"2104.00664","title":"Sampling and Filtering of Neural Machine Translation Distillation Data","created":"2021-04-01","cited_by_count":2,"area":null},{"id":"2104.08677","title":"From Fully Trained to Fully Random Embeddings: Improving Neural Machine Translation with Compact Word Embedding Tables","created":"2021-04-18","cited_by_count":2,"area":null},{"id":"2110.07816","title":"Multilingual Neural Machine Translation:Can Linguistic Hierarchies Help?","created":"2021-10-15","cited_by_count":2,"area":"distill"},{"id":"2205.01620","title":"Unifying the Convergences in Multilingual Neural Machine Translation","created":"2022-05-03","cited_by_count":2,"area":null},{"id":"2305.05226","title":"Multi-Teacher Knowledge Distillation For Text Image Machine Translation","created":"2023-05-09","cited_by_count":2,"area":"distill"},{"id":"2309.16599","title":"Unlikelihood Tuning on Negative Samples Amazingly Improves Zero-Shot Translation","created":"2023-09-28","cited_by_count":2,"area":null},{"id":"2310.13228","title":"The Less the Merrier? Investigating Language Representation in Multilingual Models","created":"2023-10-20","cited_by_count":2,"area":null},{"id":"2506.19952","title":"CycleDistill: Bootstrapping Machine Translation using LLMs with Cyclical Distillation","created":"2025-06-24","cited_by_count":2,"area":"synth"},{"id":"2602.15845","title":"KD4MT: A Survey of Knowledge Distillation for Machine Translation","created":"2026-01-22","cited_by_count":2,"area":"distill"},{"id":"2109.12507","title":"Partial to Whole Knowledge Distillation: Progressive Distilling Decomposed Knowledge Boosts Student Better","created":"2021-09-26","cited_by_count":1,"area":"distill"},{"id":"2211.11159","title":"Directed Acyclic Graph Factorization Machines for CTR Prediction via Knowledge Distillation","created":"2022-11-21","cited_by_count":1,"area":"distill"},{"id":"2305.06155","title":"Leveraging Synthetic Targets for Machine Translation","created":"2023-05-07","cited_by_count":1,"area":null},{"id":"2306.01327","title":"Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23","created":"2023-06-02","cited_by_count":1,"area":null},{"id":"2308.09327","title":"Unlimited Knowledge Distillation for Action Recognition in the Dark","created":"2023-08-18","cited_by_count":1,"area":"distill"},{"id":"2406.15476","title":"Self-Regulated Data-Free Knowledge Amalgamation for Text Classification","created":"2024-06-16","cited_by_count":1,"area":null},{"id":"2407.09020","title":"3M-Health: Multimodal Multi-Teacher Knowledge Distillation for Mental Health Detection","created":"2024-07-12","cited_by_count":1,"area":"distill"},{"id":"2510.08179","title":"Dual-granularity Sinkhorn Distillation for Enhanced Learning from Long-tailed Noisy Data","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2107.09622","title":"More Parameters? No Thanks!","created":"2021-07-20","cited_by_count":0,"area":null},{"id":"2111.10957","title":"Hierarchical Knowledge Distillation for Dialogue Sequence Labeling","created":"2021-11-22","cited_by_count":0,"area":"distill"},{"id":"2211.14920","title":"EPIK: Eliminating multi-model Pipelines with Knowledge-distillation","created":"2022-11-27","cited_by_count":0,"area":null},{"id":"2305.14230","title":"Exploring Representational Disparities Between Multilingual and Bilingual Translation Models","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2306.01261","title":"Automatic Translation of Hate Speech to Non-hate Speech in Social Media Texts","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2306.07994","title":"MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfer","created":"2023-06-12","cited_by_count":0,"area":null},{"id":"2312.08585","title":"Unraveling Key Factors of Knowledge Distillation","created":"2023-12-14","cited_by_count":0,"area":"distill"},{"id":"2401.16055","title":"Stolen Subwords: Importance of Vocabularies for Machine Translation Model Stealing","created":"2024-01-29","cited_by_count":0,"area":null},{"id":"2407.05316","title":"Leveraging Topological Guidance for Improved Knowledge Distillation","created":"2024-07-07","cited_by_count":0,"area":"distill"},{"id":"2411.12724","title":"Heuristic-Free Multi-Teacher Learning","created":"2024-11-19","cited_by_count":0,"area":null},{"id":"2507.21568","title":"Multi-Hypothesis Distillation of Multilingual Neural Translation Models for Low-Resource Languages","created":"2025-07-29","cited_by_count":0,"area":"distill"},{"id":"2605.07482","title":"SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion","created":"2026-05-08","cited_by_count":0,"area":"safety"},{"id":"2608.03480","title":"Efficient Multilingual Neural Machine Translation via Corpus-Driven Vocabulary Pruning: An English-Arabic Case Study","created":"2026-08-04","cited_by_count":0,"area":null}],"next_cursor":null}