{"total":57,"rows":[{"id":"2210.02410","title":"The Vendi Score: A Diversity Evaluation Metric for Machine Learning","created":"2022-10-05","cited_by_count":311,"area":null},{"id":"2312.15166","title":"SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling","created":"2023-12-23","cited_by_count":172,"area":null},{"id":"2103.12953","title":"Supporting Clustering with Contrastive Learning","created":"2021-03-24","cited_by_count":90,"area":null},{"id":"2204.09269","title":"A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond","created":"2022-04-20","cited_by_count":64,"area":null},{"id":"2107.11317","title":"Mixed SIGNals: Sign Language Production via a Mixture of Motion Primitives","created":"2021-07-23","cited_by_count":50,"area":null},{"id":"2205.07459","title":"Directed Acyclic Transformer for Non-Autoregressive Machine Translation","created":"2022-05-16","cited_by_count":44,"area":null},{"id":"2412.04244","title":"GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities","created":"2024-12-05","cited_by_count":33,"area":null},{"id":"2203.15108","title":"A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation","created":"2022-03-28","cited_by_count":28,"area":null},{"id":"2310.12952","title":"Cousins Of The Vendi Score: A Family Of Similarity-Based Diversity Metrics For Science And Machine Learning","created":"2023-10-19","cited_by_count":24,"area":null},{"id":"2109.01396","title":"Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT","created":"2021-09-03","cited_by_count":21,"area":null},{"id":"2106.04681","title":"Data Expansion using Back Translation and Paraphrasing for Hate Speech Detection","created":"2021-05-25","cited_by_count":20,"area":null},{"id":"2205.14333","title":"One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive Translation","created":"2022-05-28","cited_by_count":20,"area":null},{"id":"2103.15622","title":"Graph Classification by Mixture of Diverse Experts","created":"2021-03-29","cited_by_count":16,"area":null},{"id":"2406.00049","title":"QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation","created":"2024-05-28","cited_by_count":16,"area":null},{"id":"2106.01354","title":"multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning","created":"2021-06-02","cited_by_count":15,"area":null},{"id":"2302.13693","title":"Learning Topology-Specific Experts for Molecular Property Prediction","created":"2023-02-27","cited_by_count":15,"area":null},{"id":"2104.05981","title":"CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images","created":"2021-04-13","cited_by_count":14,"area":null},{"id":"2305.14926","title":"Universal Self-Adaptive Prompting","created":"2023-05-24","cited_by_count":14,"area":null},{"id":"2204.01227","title":"Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Process Priors","created":"2022-04-04","cited_by_count":13,"area":null},{"id":"2209.14627","title":"An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation","created":"2022-09-29","cited_by_count":11,"area":null},{"id":"2401.05054","title":"Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding","created":"2024-01-10","cited_by_count":11,"area":null},{"id":"2503.05318","title":"Uncertainty-Aware Decoding with Minimum Bayes Risk","created":"2025-03-07","cited_by_count":11,"area":null},{"id":"2104.10317","title":"Diverse and Specific Clarification Question Generation with Keywords","created":"2021-04-21","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":"2208.03438","title":"DeepGen: Diverse Search Ad Generation and Real-Time Customization","created":"2022-08-06","cited_by_count":10,"area":null},{"id":"2306.12719","title":"Natural Language Generation for Advertising: A Survey","created":"2023-06-22","cited_by_count":10,"area":null},{"id":"2401.01419","title":"To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation","created":"2024-01-02","cited_by_count":10,"area":null},{"id":"2402.17717","title":"AmbigNLG: Addressing Task Ambiguity in Instruction for NLG","created":"2024-02-27","cited_by_count":10,"area":null},{"id":"2501.12011","title":"Reference-free Evaluation Metrics for Text Generation: A Survey","created":"2025-01-21","cited_by_count":9,"area":null},{"id":"2106.15880","title":"Mixed Cross Entropy Loss for Neural Machine Translation","created":"2021-06-30","cited_by_count":8,"area":null},{"id":"2110.05151","title":"WeTS: A Benchmark for Translation Suggestion","created":"2021-10-11","cited_by_count":8,"area":null},{"id":"2404.12782","title":"Sentiment-oriented Transformer-based Variational Autoencoder Network for Live Video Commenting","created":"2024-04-19","cited_by_count":8,"area":null},{"id":"2211.11924","title":"Best-$k$ Search Algorithm for Neural Text Generation","created":"2022-11-22","cited_by_count":6,"area":null},{"id":"2206.00564","title":"Exploring Diversity in Back Translation for Low-Resource Machine Translation","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2305.12733","title":"MADNet: Maximizing Addressee Deduction Expectation for Multi-Party Conversation Generation","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2104.07228","title":"Sentence-Permuted Paragraph Generation","created":"2021-04-15","cited_by_count":4,"area":null},{"id":"2503.08057","title":"Odysseus Navigates the Sirens' Song: Dynamic Focus Decoding for Factual and Diverse Open-Ended Text Generation","created":"2025-03-11","cited_by_count":4,"area":null},{"id":"2504.04076","title":"Collaboration and Controversy Among Experts: Rumor Early Detection by Tuning a Comment Generator","created":"2025-04-05","cited_by_count":4,"area":null},{"id":"2104.01264","title":"Attention Forcing for Machine Translation","created":"2021-04-02","cited_by_count":3,"area":null},{"id":"2212.03747","title":"Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review","created":"2022-12-07","cited_by_count":3,"area":null},{"id":"2404.10419","title":"MAD Speech: Measures of Acoustic Diversity of Speech","created":"2024-04-16","cited_by_count":2,"area":null},{"id":"2507.10419","title":"Multiple Choice Learning of Low-Rank Adapters for Language Modeling","created":"2025-07-14","cited_by_count":2,"area":null},{"id":"2508.20567","title":"KCS: Diversify Multi-hop Question Generation with Knowledge Composition Sampling","created":"2025-08-28","cited_by_count":2,"area":null},{"id":"2105.14878","title":"Verdi: Quality Estimation and Error Detection for Bilingual Corpora","created":"2021-05-31","cited_by_count":1,"area":null},{"id":"2203.02180","title":"EAG: Extract and Generate Multi-way Aligned Corpus for Complete Multi-lingual Neural Machine Translation","created":"2022-03-04","cited_by_count":1,"area":null},{"id":"2302.02721","title":"Multipath agents for modular multitask ML systems","created":"2023-02-06","cited_by_count":1,"area":null},{"id":"2302.11078","title":"Learning Mixture Structure on Multi-Source Time Series for Probabilistic Forecasting","created":"2023-02-22","cited_by_count":1,"area":null},{"id":"2312.08900","title":"Context-PEFT: Efficient Multi-Modal, Multi-Task Fine-Tuning","created":"2023-12-14","cited_by_count":1,"area":null},{"id":"2408.14119","title":"Contrastive Learning Subspace for Text Clustering","created":"2024-08-26","cited_by_count":1,"area":null},{"id":"2410.19586","title":"Diverse Sign Language Translation","created":"2024-10-25","cited_by_count":1,"area":null},{"id":"2505.08463","title":"RepCali: High Efficient Fine-tuning Via Representation Calibration in Latent Space for Pre-trained Language Models","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2509.12677","title":"Case-Based Decision-Theoretic Decoding with Quality Memories","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2207.02534","title":"Learning to Diversify for Product Question Generation","created":"2022-07-06","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":"2305.03949","title":"Label-Free Multi-Domain Machine Translation with Stage-wise Training","created":"2023-05-06","cited_by_count":0,"area":null},{"id":"2607.10548","title":"Beyond Looking Up, Try Looking Around: Harmonizing Global Structure and Local Consistency in Optimal Transport for Short Text Clustering","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2610.00621","title":"Mixture of Decoders for Diverse Dialog Response Generation","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}