Qingyun Liu

Qingyun Liu

Auto-generated profile, based on publicly available information

Qingyun Liu

Google DeepMind, USA

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 November 2012 in Chinese Physics C
Verified
Journal Article
Closed access
PDF file
MAM. Ablikim
M. Ablikim
JBJ. Z. Bai
J. Z. Bai
YBY. Bai
Y. Bai
YBY. Ban
Y. Ban
XCXinchen Cai
Xinchen Cai
Bing-Song ZouBing-Song Zou
Bing-Song Zou
Based on 58 million J/ψ events collected by the BES II detector at the BEPC, J/ψ → Λ π+π− is observed for the first time. The branching fraction is measured to be Br(J/ψ → Λ π+π−) = (4.30±0.13±0.99)×10−3, excluding the decays to intermediate states, namely J/ψ → Ξ−+, J/ψ → Σ(1385)−(1385)+, and J/ψ → Σ(1385)+(1385)−. The branching fractions for these intermediate resonance channels are measured to be: Br(J/ψ → Ξ−+) = (0.90±0.03±0.18)×10−3, Br(J/ψ → Σ(1385)−(1385)+) = (1.23±0.07±0.30)×10−3, and Br(J/ψ → Σ(1385)+(1385)−) = (1.50±0.08±0.38)×10−3, respectively. The angular distribution is of the form ∝ (1 + αcos2θ) with α = (0.35±0.29±0.06) for J/ψ → Ξ−+, α = (−0.54±0.22±0.10) for J/ψ → Σ(1385)−(1385)+, and α = (−0.35±0.25±0.06) for J/ψ → Σ(1385)+(1385)−.

21 October 2023
Verified
Conference Paper
Open access
QLQingyun Liu
Qingyun Liu
ZZZhe Zhao
Zhe Zhao
LLLiang Liu
Liang Liu
ZZZhen Zhang
Zhen Zhang
JSJunjie Shan
Junjie Shan
ECEd H. Chi
Ed H. Chi
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.

8 October 2024
Verified
Conference Paper
Open access
YLYuening Li
Yuening Li
DUDiego Uribe
Diego Uribe
CHChuan He
Chuan He
JTJiaxi Tang
Jiaxi Tang
QLQingyun Liu
Qingyun Liu
LLLiang Liu
Liang Liu
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
Verified
Conference Paper
Open access
ZZZhen Zhang
Zhen Zhang
QLQingyun Liu
Qingyun Liu
YLYuening Li
Yuening Li
SBSourabh Bansod
Sourabh Bansod
MGMingyan Gao
Mingyan Gao
LLLiang Liu
Liang Liu
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.