{"total":96,"rows":[{"id":"2310.20453","title":"Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusion","created":"2023-10-31","cited_by_count":74,"area":"diffusion"},{"id":"2310.05632","title":"Binary Classification with Confidence Difference","created":"2023-10-09","cited_by_count":13,"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":"2306.14834","title":"Scalable Neural Contextual Bandit for Recommender Systems","created":"2023-06-26","cited_by_count":12,"area":null},{"id":"2402.09766","title":"From Variability to Stability: Advancing RecSys Benchmarking Practices","created":"2024-02-15","cited_by_count":12,"area":null},{"id":"2408.03772","title":"Relevance meets Diversity: A User-Centric Framework for Knowledge Exploration through Recommendations","created":"2024-08-07","cited_by_count":11,"area":null},{"id":"2308.08497","title":"HyperBandit: Contextual Bandit with Hypernewtork for Time-Varying User Preferences in Streaming Recommendation","created":"2023-08-14","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":"2604.08362","title":"Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces","created":"2026-04-09","cited_by_count":9,"area":null},{"id":"2406.17182","title":"Debiased Recommendation with Noisy Feedback","created":"2024-06-24","cited_by_count":8,"area":null},{"id":"2408.11202","title":"Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits","created":"2024-08-20","cited_by_count":8,"area":null},{"id":"2403.00817","title":"Doubly Calibrated Estimator for Recommendation on Data Missing Not At Random","created":"2024-02-26","cited_by_count":7,"area":null},{"id":"2405.03329","title":"Policy Learning for Balancing Short-Term and Long-Term Rewards","created":"2024-05-06","cited_by_count":7,"area":null},{"id":"2508.05633","title":"KuaiLive: A Real-time Interactive Dataset for Live Streaming Recommendation","created":"2025-08-07","cited_by_count":7,"area":null},{"id":"2512.07216","title":"MUSE: A Simple Yet Effective Multimodal Search-Based Framework for Lifelong User Interest Modeling","created":"2025-12-08","cited_by_count":6,"area":null},{"id":"2402.14664","title":"Bayesian Off-Policy Evaluation and Learning for Large Action Spaces","created":"2024-02-22","cited_by_count":5,"area":null},{"id":"2404.14961","title":"Cache-Aware Reinforcement Learning in Large-Scale Recommender Systems","created":"2024-04-23","cited_by_count":5,"area":"deeprl"},{"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":"2503.00501","title":"Qilin: A Multimodal Information Retrieval Dataset with APP-level User Sessions","created":"2025-03-01","cited_by_count":4,"area":null},{"id":"2505.12283","title":"Addressing Missing Data Issue for Diffusion-based Recommendation","created":"2025-05-18","cited_by_count":4,"area":"diffusion"},{"id":"2506.11898","title":"Martingale Posterior Neural Networks for Fast Sequential Decision Making","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2508.03668","title":"CTR-Sink: Attention Sink for Language Models in Click-Through Rate Prediction","created":"2025-08-05","cited_by_count":4,"area":null},{"id":"2508.18142","title":"Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation","created":"2025-08-25","cited_by_count":4,"area":"alignment"},{"id":"2605.07039","title":"PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents","created":"2026-05-07","cited_by_count":4,"area":"agents"},{"id":"2303.06389","title":"Uncertainty-Aware Instance Reweighting for Off-Policy Learning","created":"2023-03-11","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":"2506.16114","title":"GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks","created":"2025-06-19","cited_by_count":3,"area":"alignment"},{"id":"2510.17245","title":"On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders","created":"2025-10-20","cited_by_count":3,"area":"diffusion"},{"id":"2602.21009","title":"HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders","created":"2026-02-24","cited_by_count":3,"area":null},{"id":"2603.29112","title":"GISTBench: Evaluating LLM User Understanding via Evidence-Based Interest Verification","created":"2026-03-31","cited_by_count":3,"area":null},{"id":"2607.29241","title":"RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems","created":"2026-07-31","cited_by_count":3,"area":"agents"},{"id":"2404.19620","title":"Be Aware of the Neighborhood Effect: Modeling Selection Bias under Interference","created":"2024-04-30","cited_by_count":2,"area":null},{"id":"2408.11596","title":"Calibrating the Predictions for Top-N Recommendations","created":"2024-08-21","cited_by_count":2,"area":null},{"id":"2502.01792","title":"Policy Design for Two-sided Platforms with Participation Dynamics","created":"2025-02-03","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":"2502.08132","title":"SS4Rec: Continuous-Time Sequential Recommendation with State Space Models","created":"2025-02-12","cited_by_count":2,"area":null},{"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":"2509.03131","title":"RecBase: Generative Foundation Model Pretraining for Zero-Shot Recommendation","created":"2025-09-03","cited_by_count":2,"area":null},{"id":"2601.02386","title":"Tree of Preferences for Diversified Recommendation","created":"2025-12-24","cited_by_count":2,"area":null},{"id":"2608.08627","title":"UniMoMo: Expert Merging-Based MoE Acceleration for Large Recommendation Models","created":"2026-08-09","cited_by_count":2,"area":"moe"},{"id":"2305.16391","title":"Graph-Based Model-Agnostic Data Subsampling for Recommendation Systems","created":"2023-05-25","cited_by_count":1,"area":null},{"id":"2310.07786","title":"Non-Stationary Contextual Bandit Learning via Neural Predictive Ensemble Sampling","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2311.03382","title":"Causal Structure Representation Learning of Confounders in Latent Space for Recommendation","created":"2023-11-02","cited_by_count":1,"area":null},{"id":"2409.13175","title":"RPAF: A Reinforcement Prediction-Allocation Framework for Cache Allocation in Large-Scale Recommender Systems","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2410.01822","title":"The Importance of Causality in Decision Making: A Perspective on Recommender Systems","created":"2024-09-16","cited_by_count":1,"area":null},{"id":"2506.12389","title":"Revisiting Clustering of Neural Bandits: Selective Reinitialization for Mitigating Loss of Plasticity","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2506.14439","title":"A General Framework for Off-Policy Learning with Partially-Observed Reward","created":"2025-06-17","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":"2512.24787","title":"HiGR: Industrial-Scale Hierarchical Generative Slate Recommendation Framework in Tencent","created":"2025-12-31","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":"2602.08067","title":"Enhancing Bandit Algorithms with LLMs for Time-varying User Preferences in Streaming Recommendations","created":"2026-02-08","cited_by_count":1,"area":"alignment"},{"id":"2602.23012","title":"RQ-Reg: A Residual-Quantization-Based Framework for Continuous Value Prediction in Recommender Systems","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2603.18702","title":"Off-Policy Learning with Limited Supply","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2603.21485","title":"Off-Policy Evaluation for Ranking Policies under Deterministic Logging Policies","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2605.29500","title":"Quotient DAGs for Off-Policy Evaluation:Forward-Flow Importance Sampling and Exact Slate Propensities","created":"2026-05-28","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":"2607.01958","title":"A More Accurate Algorithm Comparison through A/B Testing using Offline Evaluation Methods","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2608.23356","title":"Hierarchical Exponential-Gaussian Mixtures for Watch-Time Distribution Prediction","created":"2026-08-24","cited_by_count":1,"area":null},{"id":"2308.08354","title":"Is Meta-Learning the Right Approach for the Cold-Start Problem in Recommender Systems?","created":"2023-08-16","cited_by_count":0,"area":null},{"id":"2309.01453","title":"Interactive Graph Convolutional Filtering","created":"2023-09-04","cited_by_count":0,"area":null},{"id":"2311.03381","title":"Separating and Learning Latent Confounders to Enhancing User Preferences Modeling","created":"2023-11-02","cited_by_count":0,"area":null},{"id":"2405.08852","title":"A Click-Through Rate Prediction Method Based on Cross-Importance of Multi-Order Features","created":"2024-05-14","cited_by_count":0,"area":null},{"id":"2408.04531","title":"AExGym: Benchmarks and Environments for Adaptive Experimentation","created":"2024-08-08","cited_by_count":0,"area":null},{"id":"2410.11188","title":"Fast Second-Order Online Kernel Learning through Incremental Matrix Sketching and Decomposition","created":"2024-10-15","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":"2501.05809","title":"AdaPRL: Adaptive Pairwise Regression Learning with Uncertainty Estimation for Universal Regression Tasks","created":"2025-01-10","cited_by_count":0,"area":null},{"id":"2506.07517","title":"Addressing Correlated Latent Exogenous Variables in Debiased Recommender Systems","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2507.01676","title":"Deep Recommender Models Inference: Automatic Asymmetric Data Flow Optimization","created":"2025-07-02","cited_by_count":0,"area":null},{"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":"2510.01606","title":"Bridging Collaborative Filtering and Large Language Models with Dynamic Alignment, Multimodal Fusion and Evidence-grounded Explanations","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2510.14641","title":"Causality Enhancement for Cross-Domain Recommendation","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2510.16076","title":"BPL: Bias-adaptive Preference Distillation Learning for Recommender System","created":"2025-10-17","cited_by_count":0,"area":"distill"},{"id":"2601.15673","title":"Enhancing guidance for missing data in diffusion-based sequential recommendation","created":"2026-01-22","cited_by_count":0,"area":"diffusion"},{"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":"2603.03770","title":"Not All Candidates are Created Equal: A Heterogeneity-Aware Approach to Pre-ranking in Recommender Systems","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.11901","title":"FlexRec: Adapting LLM-based Recommenders for Flexible Needs via Reinforcement Learning","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2603.20338","title":"Low-pass Personalized Subgraph Federated Recommendation","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2604.07096","title":"Are Stochastic Multi-objective Bandits Harder than Single-objective Bandits?","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":"2605.09040","title":"UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.11145","title":"Debiasing Message Passing to Mitigate Popularity Bias in GNN-based Collaborative Filtering","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.18509","title":"Offline Contextual Bandits in the Presence of New Actions","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.26385","title":"Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage Ranking","created":"2026-05-25","cited_by_count":0,"area":"lr"},{"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":"2606.09888","title":"SinkRec: Mitigating Semantic State Sink in Long Sequence Recommendation with Memory-Conditioned Gated Delta Networks","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2607.15242","title":"Mutable Low-Rank Sketches for Retrain-Free Recommendation","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.22012","title":"Cross-Domain Off-Policy Evaluation and Learning for Contextual Bandits","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2607.23647","title":"CALMRec: Causally Aligned Language Memory for Long-Horizon Recommendation","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2607.27577","title":"Heterogeneous Ranking in Industrial-Scale Recommender Systems: A Case Study","created":"2026-07-30","cited_by_count":0,"area":"moe"},{"id":"2608.10247","title":"DualSpectralCF: Training-Free Sign-Aware Spectral Collaborative Filtering","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.11354","title":"Inverse Theory of Mind Modeling for Content Recommendation: From Web Browsing to Dynamic Intelligent Interfaces","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.21012","title":"From a Static Multi-Level Small Semantic Codebook to a Dynamic Single-Level Large Semantic Codebook for Generative Recommendation","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.37472","title":"Do Evidence-Reading Diagnostics Improve Interface Selection in Small LLM Recommenders?","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.39007","title":"RouteRec: Behavior-Guided Sparse Routing for Sequential Recommendation","created":"2026-09-30","cited_by_count":0,"area":"moe"},{"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":"2610.15283","title":"What a Data Release Must Preserve for Off-Policy Evaluation","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}