Zhaobin Kuang

Zhaobin Kuang

Auto-generated profile, based on publicly available information

Zhaobin Kuang

Google Research, New York, NY, USA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
1 January 2023 in Mathematical Control and Related Fields
Verified
Journal Article
Open access
PDF file
ZHZhong-Jie Han
Zhong-Jie Han
ZKZhaobin Kuang
Zhaobin Kuang
QZQiong Zhang
Qiong Zhang
We study the stability of an abstract thermoelastic system, which consists of an abstract elastic equation with or without inertial term and a heat equation of Cattaneo type. A complete analysis is carried out on how the decay rates of the system depend on the parameter region and the so-called 'wave speeds'. Specifically, the parameter region for exponential stability of such a system is characterized. Furthermore, optimality of the rate of polynomial decay is obtained under certain conditions. The proofs rely on interpolation inequalities, frequency domain condition for stability, and detailed spectral analysis.

4 August 2023
Verified
Conference Paper
Open access
VBVasilisa Bashlovkina
Vasilisa Bashlovkina
RMRiley Matthews
Riley Matthews
ZKZhaobin Kuang
Zhaobin Kuang
SBSimon Baumgartner
Simon Baumgartner
MBMichael Bendersky
Michael Bendersky
We study the ability of transformer-based language models (LMs) to understand social media language. Social media (SM) language is distinct from standard written language, yet existing benchmarks fall short of capturing LM performance in this socially, economically, and politically important domain. We quantify the degree to which social media language differs from conventional language and conclude that the difference is significant both in terms of token distribution and rate of linguistic shift. Next, we introduce a new benchmark for Social MedIa Language Evaluation (SMILE) that covers four SM platforms and eleven tasks. Finally, we show that learning a tokenizer and pretraining on a mix of social media and conventional language yields an LM that outperforms the best similar-sized alternative by 4.2 points on the overall SMILE score.

13 May 2020 in arXiv
Verified
Preprint
Open access
PDF file
SGSinong Geng
Sinong Geng
ZKZhaobin Kuang
Zhaobin Kuang
PPPeggy Peissig
Peggy Peissig
DPDavid Page
David Page
We propose temporal Poisson square root graphical models (TPSQRs), a generalization of Poisson square root graphical models (PSQRs) specifically designed for modeling longitudinal event data. By estimating the temporal relationships for all possible pairs of event types, TPSQRs can offer a holistic perspective about whether the occurrences of any given event type could excite or inhibit any other type. A TPSQR is learned by estimating a collection of interrelated PSQRs that share the same template parameterization. These PSQRs are estimated jointly in a pseudo-likelihood fashion, where Poisson pseudo-likelihood is used to approximate the original more computationally-intensive pseudo-likelihood problem stemming from PSQRs. Theoretically, we demonstrate that under mild assumptions, the Poisson pseudo-likelihood approximation is sparsistent for recovering the underlying PSQR. Empirically, we learn TPSQRs from Marshfield Clinic electronic health records (EHRs) with millions of drug prescription and condition diagnosis events, for adverse drug reaction (ADR) detection. Experimental results demonstrate that the learned TPSQRs can recover ADR signals from the EHR effectively and efficiently.