{"total":57,"rows":[{"id":"2409.19913","title":"Scaling Optimal LR Across Token Horizons","created":"2024-09-30","cited_by_count":40,"area":null},{"id":"2510.24431","title":"MiniOneRec: An Open-Source Framework for Scaling Generative Recommendation","created":"2025-10-28","cited_by_count":17,"area":null},{"id":"2502.17494","title":"External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation","created":"2025-02-20","cited_by_count":13,"area":null},{"id":"2411.09852","title":"InterFormer: Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction","created":"2024-11-15","cited_by_count":8,"area":null},{"id":"2602.10016","title":"Kunlun: Establishing Scaling Laws for Massive-Scale Recommendation Systems through Unified Architecture Design","created":"2026-02-10","cited_by_count":8,"area":null},{"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":"2604.00590","title":"UniMixer: A Unified Architecture for Scaling Laws in Recommendation Systems","created":"2026-04-01","cited_by_count":7,"area":null},{"id":"2505.00347","title":"Pushing the Limits of Low-Bit Optimizers: A Focus on EMA Dynamics","created":"2025-05-01","cited_by_count":5,"area":null},{"id":"2505.22238","title":"Yambda-5B -- A Large-Scale Multi-modal Dataset for Ranking And Retrieval","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2601.20083","title":"LLaTTE: Scaling Laws for Multi-Stage Sequence Modeling in Large-Scale Ads Recommendation","created":"2026-01-27","cited_by_count":5,"area":null},{"id":"2503.18941","title":"Exploring Training and Inference Scaling Laws in Generative Retrieval","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2504.08949","title":"Large Language Model Empowered Recommendation Meets All-domain Continual Pre-Training","created":"2025-04-11","cited_by_count":4,"area":null},{"id":"2505.14057","title":"Field Matters: A Lightweight LLM-enhanced Method for CTR Prediction","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2411.13322","title":"Scaling Laws for Online Advertisement Retrieval","created":"2024-11-20","cited_by_count":3,"area":null},{"id":"2504.08169","title":"On the Practice of Deep Hierarchical Ensemble Network for Ad Conversion Rate Prediction","created":"2025-04-10","cited_by_count":3,"area":null},{"id":"2604.13737","title":"TokenFormer: Unify the Multi-Field and Sequential Recommendation Worlds","created":"2026-04-15","cited_by_count":3,"area":null},{"id":"2505.17631","title":"BehaveGPT: A Foundation Model for Large-scale User Behavior Modeling","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2509.20883","title":"RecIS: Sparse to Dense, A Unified Training Framework for Recommendation Models","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2511.06374","title":"Adaptive Regularization for Large-Scale Sparse Feature Embedding Models","created":"2025-11-09","cited_by_count":2,"area":null},{"id":"2602.11799","title":"Hi-SAM: A Hierarchical Structure-Aware Multi-modal Framework for Large-Scale Recommendation","created":"2026-02-12","cited_by_count":2,"area":null},{"id":"2604.12110","title":"SOLARIS: Speculative Offloading of Latent-bAsed Representation for Inference Scaling","created":"2026-04-13","cited_by_count":2,"area":null},{"id":"2409.04585","title":"CubicML: Automated ML for Large ML Systems Co-design with ML Prediction of Performance","created":"2024-09-06","cited_by_count":1,"area":null},{"id":"2409.15373","title":"Enhancing Performance and Scalability of Large-Scale Recommendation Systems with Jagged Flash Attention","created":"2024-09-19","cited_by_count":1,"area":null},{"id":"2505.14959","title":"Privacy Preserving Conversion Modeling in Data Clean Room","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2510.21713","title":"asLLR: LLM based Leads Ranking in Auto Sales","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2602.10455","title":"Compute Only Once: UG-Separation for Efficient Large Recommendation Models","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2605.10886","title":"LoKA: Low-precision Kernel Applications for Recommendation Models At Scale","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2605.23191","title":"Expand More, Shrink Less: Shaping Effective-Rank Dynamics for Dense Scaling in Recommendation","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2607.12281","title":"SlimPer: Make Personalization Model Slim and Smart","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2502.03417","title":"From Features to Transformers: Redefining Ranking for Scalable Impact","created":"2025-02-05","cited_by_count":0,"area":null},{"id":"2505.01616","title":"Phantora: Maximizing Code Reuse in Simulation-based Machine Learning System Performance Estimation","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2511.18331","title":"DynamiX: Dynamic Resource eXploration for Personalized Ad-Recommendations","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2602.01865","title":"GRAB: An LLM-Inspired Sequence-First Click-Through Rate Prediction Modeling Paradigm","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.07520","title":"MDL: A Unified Multi-Distribution Learner in Large-scale Industrial Recommendation through Tokenization","created":"2026-02-07","cited_by_count":0,"area":null},{"id":"2602.09194","title":"ML-DCN: Masked Low-Rank Deep Crossing Network Towards Scalable Ads Click-through Rate Prediction at Pinterest","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.14495","title":"Divine Benevolence is an $x^2$: GLUs scale asymptotically faster than MLPs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2603.02561","title":"SOLAR: SVD-Optimized Lifelong Attention for Recommendation","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.07389","title":"Feed m Birds with One Scone: Accelerating Multi-task Gradient Balancing via Bi-level Optimization","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2603.12586","title":"Deferred is Better: A Framework for Multi-Granularity Deferred Interaction of Heterogeneous Features","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.24226","title":"UniScale: Synergistic Entire Space Data and Model Scaling for Search Ranking","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2603.24963","title":"Design Once, Deploy at Scale: Template-Driven ML Development for Large Model Ecosystems","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.20847","title":"Revisiting Content-Based Music Recommendation: Efficient Feature Aggregation from Large-Scale Music Models","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2604.24073","title":"FreeScale: Distributed Training for Sequence Recommendation Models with Minimal Scaling Cost","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2604.26489","title":"Understanding DNNs in Feature Interaction Models: A Dimensional Collapse Perspective","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.13433","title":"TurboGR: An Accelerated Training System for Large-Scale Generative Recommendation","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.21752","title":"PEARL: Unbiased Percentile Estimation via Contrastive Learning for Industrial-Scale Livestream Recommendation","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.21832","title":"FLUID: From Ephemeral IDs to Multimodal Semantic Codes for Industrial-Scale Livestreaming Recommendation","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.05257","title":"Scaling Laws for Behavioral Foundation Models over User Event Sequences","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.10243","title":"DUET -- Dual User Embedding Transformers for Offsite Conversion Prediction","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.21911","title":"The Pitfall of Scaling Up: Uncovering and Mitigating Popularity Bias Amplification in Scaling Transformer-based Recommenders","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2606.28533","title":"CMSL: Constructive Multi-Sequence Learning for Recommendation Systems","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.12392","title":"MESH: Scaling Up Retrieval with Heterogeneous Content Unification","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.17017","title":"WHALE: A Scalable Unified Model for Recommendation with Wukong-HSTU Architecture","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2607.24804","title":"Bumblebee: Interleaved Mixed-Layer Building Blocks for Large-Scale Recommendation Systems","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2609.01655","title":"From Feature Interaction to Feature Transport - A Unified Block for Scalable Recommendation Models","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.34083","title":"Beyond One Epoch: Uncertainty-Weighted Sensitivity Regularization for Recommendation Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.16415","title":"Chain Dimension Scaling: Communication-Efficient Loop-Style Scaling for Industrial Short-Video Ranking","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}