{"total":72,"rows":[{"id":"2302.03328","title":"Multi-Task Recommendations with Reinforcement Learning","created":"2023-02-07","cited_by_count":26,"area":null},{"id":"2302.01680","title":"Two-Stage Constrained Actor-Critic for Short Video Recommendation","created":"2023-02-03","cited_by_count":16,"area":null},{"id":"2302.01724","title":"Reinforcing User Retention in a Billion Scale Short Video Recommender System","created":"2023-02-03","cited_by_count":15,"area":null},{"id":"2412.20211","title":"Generative Regression Based Watch Time Prediction for Short-Video Recommendation","created":"2024-12-28","cited_by_count":13,"area":null},{"id":"2508.04618","title":"HiD-VAE: Interpretable Generative Recommendation via Hierarchical and Disentangled Semantic IDs","created":"2025-08-06","cited_by_count":12,"area":null},{"id":"2510.22049","title":"Massive Memorization with Hundreds of Trillions of Parameters for Sequential Transducer Generative Recommenders","created":"2025-10-24","cited_by_count":10,"area":null},{"id":"2402.15164","title":"EasyRL4Rec: An Easy-to-use Library for Reinforcement Learning Based Recommender Systems","created":"2024-02-23","cited_by_count":9,"area":"deeprl"},{"id":"2606.26859","title":"AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems","created":"2026-06-25","cited_by_count":8,"area":null},{"id":"2302.05052","title":"Debiasing Recommendation by Learning Identifiable Latent Confounders","created":"2023-02-10","cited_by_count":7,"area":null},{"id":"2402.14230","title":"MerRec: A Large-scale Multipurpose Mercari Dataset for Consumer-to-Consumer Recommendation Systems","created":"2024-02-22","cited_by_count":6,"area":null},{"id":"2407.12223","title":"Conditional Quantile Estimation for Uncertain Watch Time in Short-Video Recommendation","created":"2024-07-17","cited_by_count":6,"area":null},{"id":"2407.13163","title":"ROLeR: Effective Reward Shaping in Offline Reinforcement Learning for Recommender Systems","created":"2024-07-18","cited_by_count":4,"area":"alignment"},{"id":"2508.11086","title":"Relative Advantage Debiasing for Watch-Time Prediction in Short-Video Recommendation","created":"2025-08-14","cited_by_count":4,"area":null},{"id":"2410.20730","title":"GPRec: Bi-level User Modeling for Deep Recommenders","created":"2024-10-28","cited_by_count":3,"area":null},{"id":"2501.10548","title":"Diffusion Models in Recommendation Systems: A Survey","created":"2025-01-17","cited_by_count":3,"area":"diffusion"},{"id":"2502.20687","title":"Unleashing the Potential of Two-Tower Models: Diffusion-Based Cross-Interaction for Large-Scale Matching","created":"2025-02-28","cited_by_count":3,"area":null},{"id":"2505.21811","title":"Revisiting Self-attention for Cross-domain Sequential Recommendation","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2507.16829","title":"You Don't Bring Me Flowers: Mitigating Unwanted Recommendations Through Conformal Risk Control","created":"2025-07-09","cited_by_count":3,"area":null},{"id":"2308.08461","title":"CDR: Conservative Doubly Robust Learning for Debiased Recommendation","created":"2023-08-13","cited_by_count":2,"area":null},{"id":"2405.01847","title":"A Model-based Multi-Agent Personalized Short-Video Recommender System","created":"2024-05-03","cited_by_count":2,"area":null},{"id":"2502.02327","title":"Policy-Guided Causal State Representation for Offline Reinforcement Learning Recommendation","created":"2025-02-04","cited_by_count":2,"area":"offlinerl"},{"id":"2505.07257","title":"DARLR: Dual-Agent Offline Reinforcement Learning for Recommender Systems with Dynamic Reward","created":"2025-05-12","cited_by_count":2,"area":"wm"},{"id":"2506.18382","title":"PERSCEN: Learning Personalized Interaction Pattern and Scenario Preference for Multi-Scenario Matching","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2508.05709","title":"G-UBS: Towards Robust Understanding of Implicit Feedback via Group-Aware User Behavior Simulation","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2603.28476","title":"With a Little Help From My Friends: Collective Manipulation in Risk-Controlling Recommender Systems","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2605.27043","title":"Causal Representation Learning for Generalisable Recommendation","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2305.15431","title":"Exploring and Exploiting Data Heterogeneity in Recommendation","created":"2023-05-21","cited_by_count":1,"area":null},{"id":"2404.08361","title":"Large-Scale Multi-Domain Recommendation: an Automatic Domain Feature Extraction and Personalized Integration Framework","created":"2024-04-12","cited_by_count":1,"area":null},{"id":"2406.04553","title":"Better Late Than Never: Formulating and Benchmarking Recommendation Editing","created":"2024-06-06","cited_by_count":1,"area":null},{"id":"2407.14094","title":"User-Creator Feature Polarization in Recommender Systems with Dual Influence","created":"2024-07-19","cited_by_count":1,"area":null},{"id":"2411.09705","title":"Residual Multi-Task Learner for Applied Ranking","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2412.18082","title":"Prompt Tuning for Item Cold-start Recommendation","created":"2024-12-24","cited_by_count":1,"area":null},{"id":"2510.12815","title":"Energy-Guided Diffusion Sampling for Long-Term User Behavior Prediction in Reinforcement Learning-based Recommendation","created":"2025-10-09","cited_by_count":1,"area":"diffusion"},{"id":"2510.16366","title":"Integrating LLM and Diffusion-Based Agents for Social Simulation","created":"2025-10-18","cited_by_count":1,"area":"agents"},{"id":"2511.04541","title":"Offline A/B Testing of Slate Recommendation Systems with LLMs: Reducing the Dependency on Pre-Collected User Interaction Data","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2511.20673","title":"Semantics Meet Signals: Dual Codebook Representationl Learning for Generative Recommendation","created":"2025-11-15","cited_by_count":1,"area":null},{"id":"2601.19585","title":"LLM-Enhanced Reinforcement Learning for Long-Term User Satisfaction in Interactive Recommendation","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2605.25290","title":"Choosing Online Experiment Designs under Interference in Ads, Recommendations, and Member-Experience Systems","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2606.07599","title":"DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regression","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2608.28905","title":"Off-Policy Evaluation for Semantic ID Recommenders: Does the Model's Own Code Hierarchy Help?","created":"2026-08-28","cited_by_count":1,"area":null},{"id":"2409.10271","title":"Causal Discovery in Recommender Systems: Example and Discussion","created":"2024-09-16","cited_by_count":0,"area":null},{"id":"2410.10835","title":"DIIT: A Domain-Invariant Information Transfer Method for Industrial Cross-Domain Recommendation","created":"2024-09-29","cited_by_count":0,"area":null},{"id":"2410.15272","title":"Performance-Driven QUBO for Recommender Systems on Quantum Annealers","created":"2024-10-20","cited_by_count":0,"area":null},{"id":"2501.18126","title":"HyperZero: A Customized End-to-End Auto-Tuning System for Recommendation with Hourly Feedback","created":"2025-01-30","cited_by_count":0,"area":null},{"id":"2503.17674","title":"MultiScale Contextual Bandits for Long Term Objectives","created":"2025-03-22","cited_by_count":0,"area":null},{"id":"2506.22112","title":"Reward Balancing Revisited: Enhancing Offline Reinforcement Learning for Recommender Systems","created":"2025-06-27","cited_by_count":0,"area":"wm"},{"id":"2508.05398","title":"On the Reliability of Sampling Strategies in Offline Recommender Evaluation","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2510.14788","title":"Cross-Scenario Unified Modeling of User Interests at Billion Scale","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2510.18239","title":"LIME: Link-based user-item Interaction Modeling with decoupled xor attention for Efficient test time scaling","created":"2025-10-21","cited_by_count":0,"area":"lr"},{"id":"2511.16248","title":"Revisiting Fairness-aware Interactive Recommendation: Item Lifecycle as a Control Knob","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2512.13300","title":"No One Left Behind: How to Exploit the Incomplete and Skewed Multi-Label Data for Conversion Rate Prediction","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2512.14733","title":"Where to Explore: A Reach and Cost-Aware Approach for Unbiased Data Collection in Recommender Systems","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2601.02368","title":"Distillation-based Scenario-Adaptive Mixture-of-Experts for the Matching Stage of Multi-scenario Recommendation","created":"2025-11-28","cited_by_count":0,"area":"moe"},{"id":"2603.03094","title":"Proactive Guiding Strategy for Item-side Fairness in Interactive Recommendation","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.03820","title":"Fairness Begins with State: Purifying Latent Preferences for Hierarchical Reinforcement Learning in Interactive Recommendation","created":"2026-03-04","cited_by_count":0,"area":"deeprl"},{"id":"2604.06956","title":"NestPipe: Large-Scale Recommendation Training on 1,500+ Accelerators via Nested Pipelining","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2605.08810","title":"Compressed Video Aggregator: Content-driven Module for Efficient Micro-Video Recommendation","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.01352","title":"FlowTime: Towards Continuous Generative Watch Time Prediction via Flow-based Personalized Priors","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.10187","title":"Decision-Calibrated Conformal Uncertainty for Pacing Decisions in Streaming Advertising","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2607.27744","title":"ROCS: Request-Oriented Compute Sharing for Efficient Large-Scale Recommendation","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.10247","title":"DualSpectralCF: Training-Free Sign-Aware Spectral Collaborative Filtering","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.16274","title":"Decoupled Temporal Encoding for Generative Recommendation","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.20801","title":"Profiling What Matters: Context-Aware Item Profiles from Large-Scale Metadata for LLM Recommenders","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.29560","title":"Which LLM for Which Work? Budgeted Model Allocation under Uncertain Evaluation","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.27201","title":"A Systematic Benchmark of Explainable Methods for Temporal Attribution in Sequential Recommendation Systems","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.28405","title":"Learning Collective Dynamics with Differentiable Gaussian Representations","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.30711","title":"Recommendation World Models for Future-State Control","created":"2026-09-25","cited_by_count":0,"area":"wm"},{"id":"2609.31890","title":"FARE: Deep Reinforcement Learning For Fair Exposure Constrained Uncertainty Aware Financial Content Personalization","created":"2026-09-25","cited_by_count":0,"area":"deeprl"},{"id":"2609.32215","title":"DP-Rec: Towards Dynamic Patching for Efficient Long-Sequence Recommendation","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.05950","title":"Discovered, Not Designed: Population Evolution for Collaborative and Compute-Intensive Model Discovery","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.08743","title":"Reinforcement Learning with Conformal Action Sets: An Application to Sequential Recommendation","created":"2026-10-06","cited_by_count":0,"area":"deeprl"},{"id":"2610.13504","title":"Beyond Temporal Proximity: Explanatory World Models for Credit Assignment in Reinforcement Learning","created":"2026-10-09","cited_by_count":0,"area":"wm"}],"next_cursor":null}