{"total":34,"rows":[{"id":"2303.13506","title":"The Quantization Model of Neural Scaling","created":"2023-03-23","cited_by_count":138,"area":null},{"id":"2403.02545","title":"Wukong: Towards a Scaling Law for Large-Scale Recommendation","created":"2024-03-04","cited_by_count":74,"area":null},{"id":"2503.10657","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","created":"2025-03-08","cited_by_count":61,"area":null},{"id":"2403.18684","title":"Scaling Laws For Dense Retrieval","created":"2024-03-27","cited_by_count":29,"area":null},{"id":"2502.18969","title":"(Mis)Fitting: A Survey of Scaling Laws","created":"2025-02-26","cited_by_count":26,"area":null},{"id":"2209.13020","title":"Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans","created":"2022-09-14","cited_by_count":23,"area":null},{"id":"2510.22037","title":"ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality","created":"2025-10-24","cited_by_count":22,"area":null},{"id":"2302.09178","title":"Improving Training Stability for Multitask Ranking Models in Recommender Systems","created":"2023-02-17","cited_by_count":13,"area":null},{"id":"2403.00793","title":"Ads Recommendation in a Collapsed and Entangled World","created":"2024-02-22","cited_by_count":13,"area":null},{"id":"2509.24244","title":"Model Merging Scaling Laws in Large Language Models","created":"2025-09-29","cited_by_count":12,"area":null},{"id":"2211.05239","title":"RecD: Deduplication for End-to-End Deep Learning Recommendation Model Training Infrastructure","created":"2022-11-09","cited_by_count":9,"area":null},{"id":"2412.07585","title":"Scaling Sequential Recommendation Models with Transformers","created":"2024-12-10","cited_by_count":7,"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":"2308.14902","title":"Ad-Rec: Advanced Feature Interactions to Address Covariate-Shifts in Recommendation Networks","created":"2023-08-28","cited_by_count":3,"area":null},{"id":"2510.02228","title":"xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2601.21285","title":"Zenith: Scaling up Ranking Models for Billion-scale Livestreaming Recommendation","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2212.03760","title":"Pivotal Role of Language Modeling in Recommender Systems: Enriching Task-specific and Task-agnostic Representation Learning","created":"2022-12-07","cited_by_count":2,"area":null},{"id":"2312.06145","title":"Proxy-based Item Representation for Attribute and Context-aware Recommendation","created":"2023-12-11","cited_by_count":2,"area":null},{"id":"2410.18111","title":"Data Efficiency for Large Recommendation Models","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2508.03854","title":"Two-dimensional Sparse Parallelism for Large Scale Deep Learning Recommendation Model Training","created":"2025-08-05","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":"2401.04408","title":"Fine-Grained Embedding Dimension Optimization During Training for Recommender Systems","created":"2024-01-09","cited_by_count":1,"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":"2601.02807","title":"COFFEE: COdesign Framework for Feature Enriched Embeddings in Ads-Ranking Systems","created":"2026-01-06","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":"2504.01506","title":"MLKV: Efficiently Scaling up Large Embedding Model Training with Disk-based Key-Value Storage","created":"2025-04-02","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":"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":"2607.27744","title":"ROCS: Request-Oriented Compute Sharing for Efficient Large-Scale Recommendation","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.23392","title":"Towards a Densing Law for User Representation Learning at Billion-Scale Capacity","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.08725","title":"BAFF: Bid-Aware Filter Family for Mitigating Training Data Interference in RTB A/B Tests","created":"2026-09-08","cited_by_count":0,"area":null}],"next_cursor":null}