All Stories

  1. PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations
  2. The Future of Personalized Universal Assistant
  3. Beyond Item Dissimilarities: Diversifying by Intent in Recommender Systems
  4. Improving Data Efficiency for Recommenders and LLMs
  5. Unpacking the Hidden Challenges in Knowledge Distillation for Online Ranking Systems
  6. Self-Auxiliary Distillation for Sample Efficient Learning in Google-Scale Recommenders
  7. Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations
  8. Serving Large User Sequence Models in Large Scale Applications
  9. Co-optimize Content Generation and Consumption in a Large Scale Video Recommendation System
  10. Multi-Task Neural Linear Bandit for Exploration in Recommender Systems
  11. Large Language Models as Data Augmenters for Cold-Start Item Recommendation
  12. Cluster Anchor Regularization to Alleviate Popularity Bias in Recommender Systems
  13. Beyond ChatBots: ExploreLLM for Structured Thoughts and Personalized Model Responses
  14. Long-Term Value of Exploration: Measurements, Findings and Algorithms
  15. Multitask Ranking System for Immersive Feed and No More Clicks: A Case Study of Short-Form Video Recommendation
  16. Online Matching: A Real-time Bandit System for Large-scale Recommendations
  17. Efficient Data Representation Learning in Google-scale Systems
  18. Improving Training Stability for Multitask Ranking Models in Recommender Systems
  19. Empowering Long-tail Item Recommendation through Cross Decoupling Network (CDN)
  20. Fresh Content Needs More Attention: Multi-funnel Fresh Content Recommendation
  21. HyperFormer: Learning Expressive Sparse Feature Representations via Hypergraph Transformer
  22. Investigating Action-Space Generalization in Reinforcement Learning for Recommendation Systems
  23. Latent User Intent Modeling for Sequential Recommenders
  24. Off-Policy Actor-critic for Recommender Systems
  25. Surrogate for Long-Term User Experience in Recommender Systems
  26. Distributionally-robust Recommendations for Improving Worst-case User Experience
  27. Learning to Augment for Casual User Recommendation
  28. Can Small Heads Help? Understanding and Improving Multi-Task Generalization
  29. Multi-Resolution Attention for Personalized Item Search
  30. Self-supervised Learning for Large-scale Item Recommendations
  31. Values of User Exploration in Recommender Systems
  32. Learning to Embed Categorical Features without Embedding Tables for Recommendation
  33. Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learning
  34. Measuring Model Fairness under Noisy Covariates: A Theoretical Perspective
  35. DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems
  36. Towards Content Provider Aware Recommender Systems
  37. A Model of Two Tales: Dual Transfer Learning Framework for Improved Long-tail Item Recommendation
  38. User Response Models to Improve a REINFORCE Recommender System
  39. Beyond Point Estimate: Inferring Ensemble Prediction Variation from Neuron Activation Strength in Recommender Systems
  40. Zero-Shot Heterogeneous Transfer Learning from Recommender Systems to Cold-Start Search Retrieval
  41. Deconfounding User Satisfaction Estimation from Response Rate Bias
  42. End-to-End Deep Attentive Personalized Item Retrieval for Online Content-sharing Platforms
  43. Mixed Negative Sampling for Learning Two-tower Neural Networks in Recommendations
  44. Learning Multi-granular Quantized Embeddings for Large-Vocab Categorical Features in Recommender Systems
  45. Off-policy Learning in Two-stage Recommender Systems
  46. Recommending what video to watch next
  47. Sampling-bias-corrected neural modeling for large corpus item recommendations
  48. Quantifying Long Range Dependence in Language and User Behavior to improve RNNs
  49. Fairness in Recommendation Ranking through Pairwise Comparisons
  50. Towards Neural Mixture Recommender for Long Range Dependent User Sequences
  51. Top-K Off-Policy Correction for a REINFORCE Recommender System
  52. Practical Diversified Recommendations on YouTube with Determinantal Point Processes
  53. Q&R
  54. Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts
  55. Evaluation and Refinement of Clustered Search Results with the Crowd
  56. The Case for Learned Index Structures
  57. Latent Cross
  58. Design for Searching & Finding
  59. Instant foodie