Ed H. Chi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ed H. Chi has a total of 133 co-authors. Here are the top co-authors by number of shared publications:
- Lichan Hong
Google, Mountain View, CA, USA
14 shared publications - Minmin Chen
Google DeepMind, Mountain View, CA, USA
11 shared publications - Derek Zhiyuan Cheng
Google DeepMind, Mountain View, CA, USA
7 shared publications - Haokai Lu
Google DeepMind, Mountain View, CA, USA
7 shared publications - Shuchao Bi
Google, USA
7 shared publications - Liang Liu
Google, Mountain View, USA
5 shared publications
Latest Publications
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1232-1241
LLM-Based User Personas for Recommendations at Scale
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1232-1241
Open AccessLLM-Based User Personas for Recommendations at Scale
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 8009-8020
Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 8009-8020
Open AccessVectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators
- Top Cited PapersOpen Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8093-8104
PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8093-8104
Top Cited PapersOpen AccessPLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations
- Open Access
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 2
The Future of Personalized Universal Assistant
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 2
Open AccessThe Future of Personalized Universal Assistant
- Open Access
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 919-922
Balancing Fine-tuning and RAG: A Hybrid Strategy for Dynamic LLM Recommendation Updates
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 919-922
Open AccessBalancing Fine-tuning and RAG: A Hybrid Strategy for Dynamic LLM Recommendation Updates
- Open Access
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 935-939
Cross-Batch Aggregation for Streaming Learning from Label Proportions in Industrial-Scale Recommendation Systems
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 935-939
Open AccessCross-Batch Aggregation for Streaming Learning from Label Proportions in Industrial-Scale Recommendation Systems
- Open Access
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2672-2681
Beyond Item Dissimilarities: Diversifying by Intent in Recommender Systems
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2672-2681
Open AccessBeyond Item Dissimilarities: Diversifying by Intent in Recommender Systems
- Open Access
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 829-831
Self-Auxiliary Distillation for Sample Efficient Learning in Google-Scale Recommenders
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 829-831
Open AccessSelf-Auxiliary Distillation for Sample Efficient Learning in Google-Scale Recommenders
- Open Access
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 758-761
Bridging the Gap: Unpacking the Hidden Challenges in Knowledge Distillation for Online Ranking Systems
Knowledge Distillation (KD) is a powerful approach for compressing a large model into a smaller, more efficient model, particularly beneficial for latency-sensitive applications like recommender systems. However, current KD research predominantly focuses on Computer Vision (CV) and NLP tasks, overlooking unique data characteristics and challenges inherent to recommender systems. This paper addresses these overlooked challenges, specifically: (1) mitigating data distribution shifts between teacher and student models, (2) efficiently identifying optimal teacher configurations within time and budgetary constraints, and (3) enabling computationally efficient and rapid sharing of teacher labels to support multiple students. We present a robust KD system developed and rigorously evaluated on multiple large-scale personalized video recommendation systems within Google. Our live experiment results demonstrate significant improvements in student model performance while ensuring consistent and reliable generation of high-quality teacher labels from a continuous data stream of data.
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 758-761
Open AccessBridging the Gap: Unpacking the Hidden Challenges in Knowledge Distillation for Online Ranking Systems
Knowledge Distillation (KD) is a powerful approach for compressing a large model into a smaller, more efficient model, particularly beneficial for latency-sensitive applications like recommender systems. However, current KD research predominantly focuses on Computer Vision (CV) and NLP tasks, overlooking unique data characteristics and challenges inherent to recommender systems. This paper addresses these overlooked challenges, specifically: (1) mitigating data distribution shifts between teacher and student models, (2) efficiently identifying optimal teacher configurations within time and budgetary constraints, and (3) enabling computationally efficient and rapid sharing of teacher labels to support multiple students. We present a robust KD system developed and rigorously evaluated on multiple large-scale personalized video recommendation systems within Google. Our live experiment results demonstrate significant improvements in student model performance while ensuring consistent and reliable generation of high-quality teacher labels from a continuous data stream of data.
- Open Access
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 762-764
Co-optimize Content Generation and Consumption in a Large Scale Video Recommendation System
Multi-task prediction models and value models are the de-facto standard ranking components in modern large-scale content recommendation systems. However, they are typically optimized to model users’ passive consumption behaviors, and rank content in a way to grow only consumption-centric values. In this talk, we discuss the key insight that it is possible to model sparse participatory content-generation actions as well and grow ecosystem value through a new ranking system. We made the following key technical contributions in this system: (1) introducing ranking for content generation based on a categorization of user participation actions of different sparsity, including proxy intent action or access point clicks. (2) improving sparse task prediction quality and stability by causal task relationship modeling, conditional loss modeling and ResNet based shared bottom network. (3) personalizing the value model to minimize conflicts between different values, through e.g. ranking inspiring content higher for users who actively generate content. (4) conducting systematic evaluation of proposed approach in a large short-form video UGC (User-Generated Content) platform.
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 762-764
Open AccessCo-optimize Content Generation and Consumption in a Large Scale Video Recommendation System
Multi-task prediction models and value models are the de-facto standard ranking components in modern large-scale content recommendation systems. However, they are typically optimized to model users’ passive consumption behaviors, and rank content in a way to grow only consumption-centric values. In this talk, we discuss the key insight that it is possible to model sparse participatory content-generation actions as well and grow ecosystem value through a new ranking system. We made the following key technical contributions in this system: (1) introducing ranking for content generation based on a categorization of user participation actions of different sparsity, including proxy intent action or access point clicks. (2) improving sparse task prediction quality and stability by causal task relationship modeling, conditional loss modeling and ResNet based shared bottom network. (3) personalizing the value model to minimize conflicts between different values, through e.g. ranking inspiring content higher for users who actively generate content. (4) conducting systematic evaluation of proposed approach in a large short-form video UGC (User-Generated Content) platform.