Teng Zhang

Teng Zhang

Auto-generated profile, based on publicly available information

Teng Zhang

Meituan, Shanghai, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
21 October 2023
Verified
Conference Paper
Open access
SLShaohua Liu
Shaohua Liu
YQYu Qi
Yu Qi
GLGen Li
Gen Li
MCMingjian Chen
Mingjian Chen
TZTeng Zhang
Teng Zhang
JLJun Lei
Jun Lei

12 April 2026
Verified
Conference Paper
Open access
RXRunze Xia
Runze Xia
YJYupeng Ji
Yupeng Ji
YZYuxi Zhou
Yuxi Zhou
HLHaodong Liu
Haodong Liu
TZTeng Zhang
Teng Zhang
PLPiji Li
Piji Li
Query-service relevance prediction in e-commerce search systems faces strict latency requirements that prevent the direct application of Large Language Models (LLMs). To bridge this gap, we propose a two-stage reasoning distillation framework to transfer reasoning capabilities from a powerful teacher LLM to a lightweight, deployment-friendly student model. In the first stage, we address the limitations of general-purpose LLMs by constructing a domain-adapted teacher model. This is achieved through a three-step process: domain-adaptive pre-training to inject platform knowledge, supervised fine-tuning to elicit reasoning skills, and preference optimization with a multi-dimensional reward model to ensure the generation of reliable and preference-aligned reasoning paths. This teacher can then automatically annotate massive query-service pairs from search logs with both relevance labels and reasoning chains. In the second stage, to address the challenges of architectural heterogeneity in standard distillation, we introduce Contrastive Reasoning Self-Distillation (CRSD). By modeling the behavior of the same student model under ''standard'' and ''reasoning-augmented'' inputs as a teacher-student relationship, CRSD enables the lightweight model to internalize the teacher's complex decision-making mechanisms without needing the explicit reasoning path at inference. Offline evaluations and online A/B testing in the Meituan search advertising system demonstrate that our framework achieves significant improvements across multiple metrics, validating its effectiveness and practical value.

12 April 2026
Verified
Conference Paper
Open access
WLWenjie Li
Wenjie Li
Shu-Tao XiaShu-Tao Xia
Shu-Tao Xia
JFJiangke Fan
Jiangke Fan
TZTeng Zhang
Teng Zhang
XWXingxing Wang
Xingxing Wang

10 November 2025
Verified
Conference Paper
Open access
JQJunyan Qiu
Junyan Qiu
ZWZe Wang
Ze Wang
FZFan Zhang
Fan Zhang
ZZZuowu Zheng
Zuowu Zheng
JZJile Zhu
Jile Zhu
XWXingxing Wang
Xingxing Wang

10 November 2025
Verified
Conference Paper
Open access
ZZZuowu Zheng
Zuowu Zheng
ZWZe Wang
Ze Wang
FYFan Yang
Fan Yang
WYWenqing Ye
Wenqing Ye
WHWeihua Huang
Weihua Huang
XWXingxing Wang
Xingxing Wang

27 September 2026
Verified
Conference Paper
Open access
ZLZerong Lan
Zerong Lan
FZFan Zhang
Fan Zhang
CCChuang Chen
Chuang Chen
THTianchun Huang
Tianchun Huang
TZTeng Zhang
Teng Zhang
XWXingxing Wang
Xingxing Wang
Emerging e-commerce platforms, such as live-streaming and Online-to-Offline (O2O) services, inherently operate under a "Container-based" display paradigm. In this setting, a critical granularity mismatch exists: the platform performs ranking and estimation at the container level (e.g., livestream rooms or stores), whereas the actual transactions occur at the item level within these containers. This structural discrepancy complicates Gross Transaction Value (GTV) estimation, introducing unique challenges including high label variance, severe label sparsity, and dynamic item heterogeneity. To address these challenges, we propose a novel framework named Hierarchical GTV Estimation (HGE). HGE employs a Hybrid Set-Aware Encoder (HSAE) to model the dynamic composition of items and feature interactions. To mitigate label variance, we introduce a Proxy-Label Learning (PLL) strategy that decomposes post-click GTV into purchase probability, quantity, and unit price. Furthermore, a Residual Correction and Ensemble Fusion (RCEF) module is designed to handle label sparsity by effectively combining item-level aggregation with container-level inference. Extensive experiments on large-scale industrial datasets demonstrate that HGE significantly outperforms state-of-the-art baselines, achieving a +0.63% lift in XAUC offline and a +1.42% increase in Revenue Per Search (RPS) in online A/B tests. HGE framework has been fully deployed into our main traffic.