All Stories

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