{"total":102,"rows":[{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045,"area":null},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358,"area":null},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290,"area":null},{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246,"area":null},{"id":"2203.16804","title":"BRIO: Bringing Order to Abstractive Summarization","created":"2022-03-31","cited_by_count":161,"area":null},{"id":"2403.06963","title":"The pitfalls of next-token prediction","created":"2024-03-11","cited_by_count":160,"area":null},{"id":"2204.01171","title":"Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation","created":"2022-04-03","cited_by_count":108,"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":"2301.13816","title":"Execution-based Code Generation using Deep Reinforcement Learning","created":"2023-01-31","cited_by_count":99,"area":null},{"id":"2504.11455","title":"SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL","created":"2025-04-15","cited_by_count":86,"area":null},{"id":"2206.00761","title":"On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting","created":"2022-06-01","cited_by_count":82,"area":null},{"id":"2305.14239","title":"On Learning to Summarize with Large Language Models as References","created":"2023-05-23","cited_by_count":80,"area":null},{"id":"2306.00186","title":"Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2104.05336","title":"Machine Translation Decoding beyond Beam Search","created":"2021-04-12","cited_by_count":55,"area":null},{"id":"2302.06461","title":"A Study on ReLU and Softmax in Transformer","created":"2023-02-13","cited_by_count":53,"area":null},{"id":"2108.11179","title":"Recall@k Surrogate Loss with Large Batches and Similarity Mixup","created":"2021-08-25","cited_by_count":49,"area":null},{"id":"2212.10938","title":"Critic-Guided Decoding for Controlled Text Generation","created":"2022-12-21","cited_by_count":45,"area":null},{"id":"2106.15691","title":"Deep Multiagent Reinforcement Learning: Challenges and Directions","created":"2021-06-29","cited_by_count":42,"area":null},{"id":"2101.10506","title":"Finite Sample Analysis of Two-Time-Scale Natural Actor-Critic Algorithm","created":"2021-01-26","cited_by_count":39,"area":null},{"id":"2106.00327","title":"Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs","created":"2021-06-01","cited_by_count":39,"area":null},{"id":"2106.07704","title":"Efficient (Soft) Q-Learning for Text Generation with Limited Good Data","created":"2021-06-14","cited_by_count":37,"area":null},{"id":"2106.08942","title":"Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation","created":"2021-06-16","cited_by_count":33,"area":null},{"id":"2310.20703","title":"Vanishing Gradients in Reinforcement Finetuning of Language Models","created":"2023-10-31","cited_by_count":27,"area":null},{"id":"2102.09318","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm","created":"2021-02-18","cited_by_count":26,"area":null},{"id":"2501.17202","title":"Audio Large Language Models Can Be Descriptive Speech Quality Evaluators","created":"2025-01-27","cited_by_count":25,"area":null},{"id":"2212.05301","title":"Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning","created":"2022-12-10","cited_by_count":22,"area":null},{"id":"2104.02726","title":"Creativity and Machine Learning: A Survey","created":"2021-04-06","cited_by_count":21,"area":null},{"id":"2103.14026","title":"AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks","created":"2021-03-25","cited_by_count":19,"area":null},{"id":"2406.10278","title":"Prompt-Based Length Controlled Generation with Multiple Control Types","created":"2024-06-12","cited_by_count":19,"area":null},{"id":"2106.08122","title":"Sequence-Level Training for Non-Autoregressive Neural Machine Translation","created":"2021-06-15","cited_by_count":18,"area":null},{"id":"2108.12472","title":"ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models","created":"2021-08-27","cited_by_count":16,"area":null},{"id":"2110.06997","title":"Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits","created":"2021-10-13","cited_by_count":16,"area":null},{"id":"2106.03816","title":"Diversity driven Query Rewriting in Search Advertising","created":"2021-06-07","cited_by_count":15,"area":null},{"id":"2108.12121","title":"Reinforcement Learning-powered Semantic Communication via Semantic Similarity","created":"2021-08-27","cited_by_count":15,"area":null},{"id":"2305.08706","title":"Understanding and Bridging the Modality Gap for Speech Translation","created":"2023-05-15","cited_by_count":15,"area":null},{"id":"2308.12030","title":"Prompt-Based Length Controlled Generation with Reinforcement Learning","created":"2023-08-23","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":"2210.08708","title":"Teacher Forcing Recovers Reward Functions for Text Generation","created":"2022-10-17","cited_by_count":11,"area":null},{"id":"2106.04985","title":"Energy-Based Models for Code Generation under Compilability Constraints","created":"2021-06-09","cited_by_count":10,"area":null},{"id":"2304.09185","title":"Token Imbalance Adaptation for Radiology Report Generation","created":"2023-04-18","cited_by_count":10,"area":null},{"id":"2307.16246","title":"DRL4Route: A Deep Reinforcement Learning Framework for Pick-up and Delivery Route Prediction","created":"2023-07-30","cited_by_count":10,"area":null},{"id":"2308.00031","title":"Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges","created":"2023-07-31","cited_by_count":10,"area":null},{"id":"2311.01388","title":"Time-series Generation by Contrastive Imitation","created":"2023-11-02","cited_by_count":9,"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":"2212.04257","title":"Momentum Calibration for Text Generation","created":"2022-12-08","cited_by_count":8,"area":null},{"id":"2407.02518","title":"INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness","created":"2024-06-23","cited_by_count":8,"area":null},{"id":"2204.07696","title":"Efficient Reinforcement Learning for Unsupervised Controlled Text Generation","created":"2022-04-16","cited_by_count":7,"area":null},{"id":"2207.08583","title":"MAD for Robust Reinforcement Learning in Machine Translation","created":"2022-07-18","cited_by_count":7,"area":null},{"id":"2103.09656","title":"Set-to-Sequence Methods in Machine Learning: a Review","created":"2021-03-17","cited_by_count":6,"area":null},{"id":"2210.11017","title":"Multi-Granularity Optimization for Non-Autoregressive Translation","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2308.01872","title":"Thespian: Multi-Character Text Role-Playing Game Agents","created":"2023-08-03","cited_by_count":6,"area":null},{"id":"2407.01490","title":"LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectives","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2108.00138","title":"Learning to Control DC Motor for Micromobility in Real Time with Reinforcement Learning","created":"2021-07-31","cited_by_count":5,"area":null},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","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":"2206.13974","title":"Joint Generator-Ranker Learning for Natural Language Generation","created":"2022-06-28","cited_by_count":4,"area":null},{"id":"2310.17217","title":"Beyond MLE: Convex Learning for Text Generation","created":"2023-10-26","cited_by_count":4,"area":null},{"id":"2103.11795","title":"Simpson's Bias in NLP Training","created":"2021-03-13","cited_by_count":3,"area":null},{"id":"2104.01264","title":"Attention Forcing for Machine Translation","created":"2021-04-02","cited_by_count":3,"area":null},{"id":"2202.04847","title":"A Survey on Artificial Intelligence for Source Code: A Dialogue Systems Perspective","created":"2022-02-10","cited_by_count":3,"area":null},{"id":"2202.07138","title":"Integrating AI Planning with Natural Language Processing: A Combination of Explicit and Tacit Knowledge","created":"2022-02-15","cited_by_count":3,"area":null},{"id":"2211.16863","title":"Rephrasing the Reference for Non-Autoregressive Machine Translation","created":"2022-11-30","cited_by_count":3,"area":null},{"id":"2307.08416","title":"Enhancing Supervised Learning with Contrastive Markings in Neural Machine Translation Training","created":"2023-07-17","cited_by_count":3,"area":null},{"id":"2310.15594","title":"Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2101.08675","title":"Adversarial Machine Learning in Text Analysis and Generation","created":"2021-01-14","cited_by_count":2,"area":null},{"id":"2109.09371","title":"Learning Natural Language Generation from Scratch","created":"2021-09-20","cited_by_count":2,"area":null},{"id":"2209.07873","title":"Adaptive Natural Language Generation for Task-oriented Dialogue via Reinforcement Learning","created":"2022-09-16","cited_by_count":2,"area":null},{"id":"2304.12330","title":"Parallel bootstrap-based on-policy deep reinforcement learning for continuous flow control applications","created":"2023-04-24","cited_by_count":2,"area":null},{"id":"2305.17052","title":"A Framework for Incentivized Collaborative Learning","created":"2023-05-26","cited_by_count":2,"area":null},{"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":"2311.04921","title":"Successor Features for Efficient Multisubject Controlled Text Generation","created":"2023-11-03","cited_by_count":2,"area":null},{"id":"2404.01706","title":"Polarity Calibration for Opinion Summarization","created":"2024-04-02","cited_by_count":2,"area":null},{"id":"2409.14013","title":"ChronoGAN: Supervised and Embedded Generative Adversarial Networks for Time Series Generation","created":"2024-09-21","cited_by_count":2,"area":null},{"id":"2101.09698","title":"Fast Sequence Generation with Multi-Agent Reinforcement Learning","created":"2021-01-24","cited_by_count":1,"area":null},{"id":"2102.11403","title":"Exploring Supervised and Unsupervised Rewards in Machine Translation","created":"2021-02-22","cited_by_count":1,"area":null},{"id":"2105.08244","title":"PoBRL: Optimizing Multi-Document Summarization by Blending Reinforcement Learning Policies","created":"2021-05-18","cited_by_count":1,"area":null},{"id":"2106.14295","title":"A Reinforcement Learning Approach for Sequential Spatial Transformer Networks","created":"2021-06-27","cited_by_count":1,"area":null},{"id":"2109.06308","title":"Improving Scheduled Sampling with Elastic Weight Consolidation for Neural Machine Translation","created":"2021-09-13","cited_by_count":1,"area":null},{"id":"2109.09307","title":"Assisted Learning for Organizations with Limited Imbalanced Data","created":"2021-09-20","cited_by_count":1,"area":null},{"id":"2207.11161","title":"Lagrangian Method for Q-Function Learning (with Applications to Machine Translation)","created":"2022-07-22","cited_by_count":1,"area":null},{"id":"2209.08206","title":"Selective Token Generation for Few-shot Natural Language Generation","created":"2022-09-17","cited_by_count":1,"area":null},{"id":"2303.14480","title":"GANTEE: Generative Adversatial Network for Taxonomy Entering Evaluation","created":"2023-03-25","cited_by_count":1,"area":null},{"id":"2305.13667","title":"Optimizing Non-Autoregressive Transformers with Contrastive Learning","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2308.08442","title":"Mitigating the Exposure Bias in Sentence-Level Grapheme-to-Phoneme (G2P) Transduction","created":"2023-08-16","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":"2506.17424","title":"Sequence-to-Sequence Models with Attention Mechanistically Map to the Architecture of Human Memory Search","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2511.15716","title":"MACIE: Multi-Agent Causal Intelligence Explainer for Collective Behavior Understanding","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2605.07244","title":"Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2607.06818","title":"Ad Headline Generation using Self-Critical Masked Language Model","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2101.03236","title":"SDA: Improving Text Generation with Self Data Augmentation","created":"2021-01-02","cited_by_count":0,"area":null},{"id":"2103.11603","title":"Alleviate Exposure Bias in Sequence Prediction \\\\ with Recurrent Neural Networks","created":"2021-03-22","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":"2301.00688","title":"Active Learning for Neural Machine Translation","created":"2022-12-30","cited_by_count":0,"area":null},{"id":"2306.16503","title":"SARC: Soft Actor Retrospective Critic","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2308.07486","title":"O-1: Self-training with Oracle and 1-best Hypothesis","created":"2023-08-14","cited_by_count":0,"area":null},{"id":"2405.01601","title":"Efficient Sample-Specific Encoder Perturbations","created":"2024-05-01","cited_by_count":0,"area":null},{"id":"2405.02480","title":"A Network Simulation of OTC Markets with Multiple Agents","created":"2024-05-03","cited_by_count":0,"area":null},{"id":"2405.11819","title":"Beyond MLE: Investigating SEARNN for Low-Resourced Neural Machine Translation","created":"2024-05-20","cited_by_count":0,"area":null},{"id":"2409.19572","title":"Mitigating the Negative Impact of Over-association for Conversational Query Production","created":"2024-09-29","cited_by_count":0,"area":null}],"next_cursor":"100"}