Liang Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Liang Liu has a total of 54 co-authors. Here are the top co-authors by number of shared publications:
- Yuening Li
Google, Mountain View, USA
8 shared publications - Ed H. Chi
Google DeepMind, Mountain View, CA, USA
5 shared publications - Shuchao Bi
Google, USA
5 shared publications - Chuan He
Google, Mountain View, CA, USA
4 shared publications - Diego Uribe Mora
YouTube, Google, Mountain View, CA, USA
3 shared publications - Lichan Hong
Google, Mountain View, CA, USA
3 shared publications
Latest Publications
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1199-1205
Interest Sequence for User Modeling in Industrial Short-Form Video Recommendation
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1199-1205
Open AccessInterest Sequence for User Modeling in Industrial Short-Form Video Recommendation
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7456-7464
Addressing Intent Dissonance in Cross-Domain Distillation on YouTube
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7456-7464
Open AccessAddressing Intent Dissonance in Cross-Domain Distillation on YouTube
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4902-4906
Beyond Item IDs: Scaling Short-Form-Video Recommendation via Semantic-Native Long Sequence Modeling
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4902-4906
Open AccessBeyond Item IDs: Scaling Short-Form-Video Recommendation via Semantic-Native Long Sequence Modeling
- Open Access
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1014-1016
Minimize Negative Experiences in Video Recommendation Systems with Multimodal Large Language Models
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1014-1016
Open AccessMinimize Negative Experiences in Video Recommendation Systems with Multimodal Large Language Models
- 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.
- Open Access
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 832-834
Short-form Video Needs Long-term Interests: An Industrial Solution for Serving Large User Sequence Models
Sequential models are invaluable for powering personalized recommendation systems. In the context of short-form video (SFV) feeds, where user behavior history is typically longer, systems must be able to understand users’ long-term interests. However, deploying large sequence models to extensive web-scale applications faces challenges due to high serving cost. To address this, we propose an industrial framework designed for efficiently serving large user sequence models. Specifically, the proposed infrastructure decouples serving of the user sequence model and the main recommendation model, with the user sequence model being served offline (asynchronously) with periodical refresh. The proposed infrastructure is also model-agnostic; thus, it can be used to support any type of user sequence models (even LLMs) with controllable costs. Empirical results show that large user models deployed with our framework significantly and consistently enhance the quality of the main recommendation model with minimal serving costs increase.
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 832-834
Open AccessShort-form Video Needs Long-term Interests: An Industrial Solution for Serving Large User Sequence Models
Sequential models are invaluable for powering personalized recommendation systems. In the context of short-form video (SFV) feeds, where user behavior history is typically longer, systems must be able to understand users’ long-term interests. However, deploying large sequence models to extensive web-scale applications faces challenges due to high serving cost. To address this, we propose an industrial framework designed for efficiently serving large user sequence models. Specifically, the proposed infrastructure decouples serving of the user sequence model and the main recommendation model, with the user sequence model being served offline (asynchronously) with periodical refresh. The proposed infrastructure is also model-agnostic; thus, it can be used to support any type of user sequence models (even LLMs) with controllable costs. Empirical results show that large user models deployed with our framework significantly and consistently enhance the quality of the main recommendation model with minimal serving costs increase.
- Open Access
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1213-1215
VideoRecSys + LargeRecSys 2024
With the exponential growth of video and other content across various domains including entertainment, e-commerce, education and social media, there is a growing need for personalized content recommendations that are relevant to users’ interests. However, building effective and scalable content recommender systems is challenging due to factors such as the vast volume of content, diversity of user preferences, inherent noise and bias in data, and the need for real-time recommendations. The VideoRecSys + LargeRecSys joint workshop aims to bring together researchers, practitioners and industry experts to discuss the latest trends, challenges and opportunities in large-scale content recommendation systems. It will provide a forum for participants to delve into nuanced topics critical to advancing large-scale content recommendations, including the use of modern innovations like large language models (LLMs) to enhance personalization and efficiency. The workshop also aims to foster collaboration within the growing video recommender systems community and inspire fresh avenues of applied research in this rapidly evolving domain [5, 7]. This workshop will feature multiple domain experts from industry and academia leading discussions about their work on large-scale recommender systems. In addition to speaker-led sessions, the workshop will include a space for the RecSys community to contribute their own research and findings on developing recommender systems solutions at scale.
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1213-1215
Open AccessVideoRecSys + LargeRecSys 2024
With the exponential growth of video and other content across various domains including entertainment, e-commerce, education and social media, there is a growing need for personalized content recommendations that are relevant to users’ interests. However, building effective and scalable content recommender systems is challenging due to factors such as the vast volume of content, diversity of user preferences, inherent noise and bias in data, and the need for real-time recommendations. The VideoRecSys + LargeRecSys joint workshop aims to bring together researchers, practitioners and industry experts to discuss the latest trends, challenges and opportunities in large-scale content recommendation systems. It will provide a forum for participants to delve into nuanced topics critical to advancing large-scale content recommendations, including the use of modern innovations like large language models (LLMs) to enhance personalization and efficiency. The workshop also aims to foster collaboration within the growing video recommender systems community and inspire fresh avenues of applied research in this rapidly evolving domain [5, 7]. This workshop will feature multiple domain experts from industry and academia leading discussions about their work on large-scale recommender systems. In addition to speaker-led sessions, the workshop will include a space for the RecSys community to contribute their own research and findings on developing recommender systems solutions at scale.
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 5723-5730
Multi-Task Neural Linear Bandit for Exploration in Recommender Systems
Exposure bias and its induced feedback loop effect are well-known problems in recommender systems. Exploration is believed to be the key to break such feedback loops. While classical contextual bandit algorithms such as Upper-Confidence-Bound and Thompson Sampling have been successful in addressing the exploration-exploitation trade-off in the single-task settings with one clear reward signal, modern recommender systems often leverage multiple rich sources of feedback such as clicks, likes, dislikes, shares, satisfaction survey responses, and employ multi-task learning in practice. It is unclear how one can incorporate exploration in the multi-task setup with different objectives. In this paper, we study an efficient bandit algorithm tailored to multi-task recommender systems, named Multi-task Neural Linear Bandit (mtNLB). In particular, we investigate efficient feature embeddings in the multi-task setups that could be used as contextual features in the Neural Linear Bandit, a contextual bandit algorithm that nicely combines the representation power from DNN and simplicity in uncertainty calculation from linear models. We further study cost-effective approximations of the uncertainty estimate and principled ways to incorporate uncertainty into the multi-task scoring of items. To showcase the efficacy of our proposed method, we conduct live experiments on a large-scale commercial recommendation platform that serves billions of users. We evaluate the quality of the uncertainty estimate and demonstrate its ability to improve exploration across the different dimensions of the reward signals in comparison to baseline approaches.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 5723-5730
Open AccessMulti-Task Neural Linear Bandit for Exploration in Recommender Systems
Exposure bias and its induced feedback loop effect are well-known problems in recommender systems. Exploration is believed to be the key to break such feedback loops. While classical contextual bandit algorithms such as Upper-Confidence-Bound and Thompson Sampling have been successful in addressing the exploration-exploitation trade-off in the single-task settings with one clear reward signal, modern recommender systems often leverage multiple rich sources of feedback such as clicks, likes, dislikes, shares, satisfaction survey responses, and employ multi-task learning in practice. It is unclear how one can incorporate exploration in the multi-task setup with different objectives. In this paper, we study an efficient bandit algorithm tailored to multi-task recommender systems, named Multi-task Neural Linear Bandit (mtNLB). In particular, we investigate efficient feature embeddings in the multi-task setups that could be used as contextual features in the Neural Linear Bandit, a contextual bandit algorithm that nicely combines the representation power from DNN and simplicity in uncertainty calculation from linear models. We further study cost-effective approximations of the uncertainty estimate and principled ways to incorporate uncertainty into the multi-task scoring of items. To showcase the efficacy of our proposed method, we conduct live experiments on a large-scale commercial recommendation platform that serves billions of users. We evaluate the quality of the uncertainty estimate and demonstrate its ability to improve exploration across the different dimensions of the reward signals in comparison to baseline approaches.
- Open Access
- 4 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 636-644
Long-Term Value of Exploration: Measurements, Findings and Algorithms
- 4 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 636-644
Open AccessLong-Term Value of Exploration: Measurements, Findings and Algorithms
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4709-4716
Multitask Ranking System for Immersive Feed and No More Clicks: A Case Study of Short-Form Video Recommendation
In recent years, social media users spend significant amount of time on Short-Form Video (SFV) platforms. Its success in creating an immersive viewership experience is not only from the content, but also due to its unique UI innovation: instead of providing choices for users to click, SFV platforms actively recommend content to users to watch one at a time. In this paper, we highlight unique challenges rooted from such UI changes for SFV recommendation system design. Firstly, there is yet much unexplored for sources of system biases under the new UI, as there are no clicks nor the common click-based position biases. Additionally, when training multiple types of user activities, positive labels for activities like sharing and commenting can be much sparser and more skewed than traditional click-based recommendation systems, as the latter can filter non-click impressions when generating "post-click" activities. To tackle these challenges, we introduce a unified multi-task ranking framework which puts two novel components all together into an overall system for SFV recommendation. First, we identify that there are position biases of SFVs in the recommendation sequence, namely "watch trail biases", and introduce biases correction using trail-related information. Second, to get the most benefits from multi-task learning, especially co-training tasks with extremely skewed and sparse labels, we adapt a disentangle regularization to mitigate task conflicts, introduce loss upweighting for sparse task co-training and adopt a meta-learning algorithm for efficient weight selection. We demonstrate the effectiveness and efficiency of the framework on one of today's largest SFV platforms. Our framework has been deployed to the production system for more than 6 months.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4709-4716
Open AccessMultitask Ranking System for Immersive Feed and No More Clicks: A Case Study of Short-Form Video Recommendation
In recent years, social media users spend significant amount of time on Short-Form Video (SFV) platforms. Its success in creating an immersive viewership experience is not only from the content, but also due to its unique UI innovation: instead of providing choices for users to click, SFV platforms actively recommend content to users to watch one at a time. In this paper, we highlight unique challenges rooted from such UI changes for SFV recommendation system design. Firstly, there is yet much unexplored for sources of system biases under the new UI, as there are no clicks nor the common click-based position biases. Additionally, when training multiple types of user activities, positive labels for activities like sharing and commenting can be much sparser and more skewed than traditional click-based recommendation systems, as the latter can filter non-click impressions when generating "post-click" activities. To tackle these challenges, we introduce a unified multi-task ranking framework which puts two novel components all together into an overall system for SFV recommendation. First, we identify that there are position biases of SFVs in the recommendation sequence, namely "watch trail biases", and introduce biases correction using trail-related information. Second, to get the most benefits from multi-task learning, especially co-training tasks with extremely skewed and sparse labels, we adapt a disentangle regularization to mitigate task conflicts, introduce loss upweighting for sparse task co-training and adopt a meta-learning algorithm for efficient weight selection. We demonstrate the effectiveness and efficiency of the framework on one of today's largest SFV platforms. Our framework has been deployed to the production system for more than 6 months.