About Publications Professional Experience CV

photo

xinluzhang970501 AT gmail DOT com

Xinlu Zhang 张心璐

xinluzhang970501 AT gmail DOT com / LinkedIn / GitHub / Google Scholar / CV

I’m a Senior Machine Learning Engineer at LinkedIn, where I develop and conduct applied research on LLM‑based multi‑agent systems and semantic search solutions. Previously, I earned my Ph.D. in Computer Science at the University of California, Santa Barbara under the supervision of Prof. Linda R. Petzold. Before that, I also hold an M.S. in Statistics and a B.S. in Statistics & Mathematics from Indiana University, Bloomington.

I'm on the Job Market!

Research Interests:

My research focuses on building efficient, reliable, and domain-aware LLMs through post-training and evaluation to boost reasoning, instruction-following, and domain expertise. Broader interests include multimodal learning, time-series modeling, and label-efficient training.

Publications and Preprints

• Post Training & Data Recipe for LLMs

Unveiling the Impact of Coding Data Instruction Fine‑Tuning on Large Language Models Reasoning
Xinlu Zhang, Zhiyu Zoey Chen, Xi Ye, Lichang Chen, Xianjun Yang, William Yang Wang, Linda Petzold
Proceedings of AAAI 2025 (oral) [arXiv]

Explanations from Large Language Models Make Small Reasoners Better
Shiyang Li, Jianshu Chen, Yelong Shen, Zhiyu Chen, Xinlu Zhang, Zekun Li, Hong Wang, Jing Qian, Baolin Peng, Yi Mao, Wenhu Chen, Xifeng Yan
AAAI 2024 Workshop on Sustainable AI (SAI‑AAAI2024) [arXiv]

AlpaCare: Instruction‑tuned Large Language Models for Medical Applications
Xinlu Zhang, Chenxin Tian, Xianjun Yang, Lichang Chen, Zekun Li, Linda Petzold
ICLR 2025 Open Science for Foundation Models (SCI‑FM) Workshop

[arXiv] [code]

Enhancing Small Medical Learners with Privacy‑preserving Contextual Prompting
Xinlu Zhang, Shiyang Li, Xianjun Yang, Chenxin Tian, Yao Qin, Linda Petzold
Proceedings of ICLR 2024

[arXiv]

• LLM Evaluation & Analysis

Do Retrieval‑Augmented Language Models Adapt to Varying User Needs?
Peilin Wu*, Xinlu Zhang*, Wenhao Yu, Xingyu Liu, Xinya Du, Zhiyu Zoey Chen
Under review

[arXiv]

GPT-4V(ision) as a Generalist Evaluator for Vision-Language Tasks
Xinlu Zhang*, Yujie Lu*, Weizhi Wang*, An Yan, Jun Yan, Heng Wang, Xifeng Yan, William Yang Wang, Linda Petzold
Preprint

[arXiv]

CBT‑Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy
Mian Zhang, Xianjun Yang, Xinlu Zhang, Travis Labrum, Jamie C. Chiu, Shaun M. Eack, Fei Fang, William Yang Wang, Zhiyu Zoey Chen
Proceedings of NAACL 2025

[arXiv]

Exploring the Limits of ChatGPT for Query or Aspect‑based Text Summarization
Xianjun Yang, Yan Li, Xinlu Zhang, Haifeng Chen, Wei Wang
Preprint

[arXiv]

A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Law
Zhiyu Zoey Chen, Jing Ma, Xinlu Zhang, Nan Hao, An Yan, Armineh Nourbakhsh, Xianjun Yang, Julian McAuley, Linda Petzold, William Yang Wang
TMLR 2024 (Survey Certification)

[arXiv] [code]

• Architectures, Datasets & Domain Applications

Improving Medical Predictions by Irregular Multimodal Electronic Health Records Modeling
Xinlu Zhang*, Shiyang Li*, Zhiyu Zoey Chen, Xifeng Yan, Linda Petzold
Proceedings of ICML 2023

[arXiv] [code]

PcMSP: A Dataset for Scientific Action Graphs Extraction from Polycrystalline Materials Synthesis Procedure Text
Xianjun Yang, Ya Zhuo, Julia Zuo, Xinlu Zhang, Stephen Wilson, Linda Petzold
Findings of EMNLP 2022

[arXiv] [code]

Domain Adaptation for Trauma Mortality Prediction in EHRs with Feature Disparity
Xinlu Zhang, Shiyang Li, Zhuowei Cheng, Rachael Callcut, Linda Petzold
Proceedings of BIBM 2021

[arXiv]

An Analysis of Relation Extraction from Wet Lab Protocols
Xianjun Yang, Xinlu Zhang, Julia Zuo, Stephen Wilson, Linda Petzold
Proceedings of BigData 2021

[arXiv]

BERTSurv: BERT‑Based Survival Models for Predicting Outcomes of Trauma Patients
Yun Zhao,, Qinghang Hong, Xinlu Zhang, Yu Deng, Yuqing Wang, Paul K. Hansma, Linda Petzold
Proceedings of ICDM 2021

[arXiv]

Professional Experience

  • Senior Machine Learning Engineer

    LinkedIn, Sunnyvale, CA · Sep 2024 – Present

    • Develop LLM-based multi-agent systems to optimize LinkedIn’s hiring process, incorporating customized recruiter preferences.
    • Conduct applied research on robust semantic search solutions.
  • Research Scientist Intern

    Meta Reality Labs, Burlingame, CA · Sep 2023 – Dec 2023

  • Machine Learning Engineer Intern

    LinkedIn, Sunnyvale, CA · Jun 2023 – Sep 2023

  • Machine Learning Engineer Intern

    LinkedIn, Sunnyvale, CA · Jun 2022 – Sep 2022

Professional Services

- Conferences Reviewer: ACL Rolling Review, NeurIPS 2023-2024, ICLR 2023-2024, ICML 2024-2025, AAAI 2023-2025

modified from © Yangqing Jia 2013

Total Visits: