Zhengxin Zhang

Zhengxin Zhang

zz865@cornell.edu

Visitor Map

About Me

I am a second-year CS PhD student at Cornell University, advised by Prof. Claire Cardie. Previously, I was a research assistant at Carnegie Mellon University supervised by Prof. Zhihao Jia. I obtained my MS at Tsinghua University supervised by Prof. Yong Jiang, and my BS at the CS department of Xidian University, where I was supervised by Prof. Yuesheng Xu.

My research focuses on large language models — particularly LLM reasoning (self-play, RL post-training), robustness under noisy or adversarial inputs, and efficient training and serving.

I'm always open to collaboration — feel free to drop me an email!

📍 Bill and Melinda Gates Hall, G23 · Campus Rd, Ithaca, NY 14853

News

[Apr 2026] Released Research Arena — an evaluation of CLI-based AI agents (Claude Code, Codex, Kimi Code) on end-to-end scientific research across 13 CS domains. Read the analysis →

[Apr 2026] Two papers accepted to ACL 2026 Findings: Better LLM Reasoning via Dual-play and GSM-Noise: Exploring and Enhancing Large Language Models' Reasoning under Noisy Inputs. See you in San Diego!

[Nov 2025] We released Better LLM Reasoning via Dual-play, a framework that trains two nearly identical models adversarially, enabling them to co-evolve through iterative competition without external supervision. Read the blog post →

Publications

Preprints

  1. Towards More Robust Retrieval-Augmented Generation: Evaluating RAG Under Adversarial Poisoning Attacks
    Jinyan Su, Jin Peng Zhou, Zhengxin Zhang, Preslav Nakov, Claire Cardie
    arXiv
  2. Graph-based Multi-Task Learning Framework for Model Generalization across Network Topologies
    Jingyu Xiao, Qing Li, Zhengxin Zhang, Dan Zhao, Yong Jiang

2026

  1. Better LLM Reasoning via Dual-play
    Zhengxin Zhang*, Chengyu Huang*, Aochong Oliver Li, Claire Cardie
    Findings of ACL, 2026
    arXiv / Blog / Code
  2. GSM-Noise: Exploring and Enhancing Large Language Models' Reasoning under Noisy Inputs
    Zhengxin Zhang*, Chengyu Huang*, Xufu Liu, Dan Zhao, Jinyan Su, Claire Cardie
    Findings of ACL, 2026
    OpenReview
  3. HumanGuideNet: Adapter-Based Alignment of Deep Neural Networks with Human Similarity Judgments
    Xufu Liu, Yifan Yang, Zhengxin Zhang
    WACV, Mar 2026
  4. HAPO: Training Language Models to Reason Concisely via History-Aware Policy Optimization
    Chengyu Huang*, Zhengxin Zhang*, Claire Cardie
    AAAI, Jan 2026
    arXiv

2025

  1. Learning-Enhanced High-Throughput Pattern Matching Based on Programmable Data Plane
    Guanglin Duan*, Yucheng Huang*, Zhengxin Zhang*, Qing Li, Dan Zhao, Yong Jiang
    USENIX ATC, July 2025
    USENIX

2024

  1. Quantized Side Tuning: Fast and Efficient Tuning of Quantized Large Language Models ★ Outstanding Paper
    Zhengxin Zhang, Dan Zhao, Xupeng Miao, Gabriele Oliaro, Qing Li, Yong Jiang, Zhihao Jia
    ACL, Aug 2024 · Oral presentation
    arXiv
  2. SpecInfer: Accelerating Large Language Model Serving with Tree-Based Speculative Inference and Verification
    Xupeng Miao, Gabriele Oliaro, Zhihao Zhang, Xinhao Cheng, Zeyu Wang, Zhengxin Zhang, Rae Ying Yee Wong, Alan Zhu, Lijie Yang, Xiaoxiang Shi, Chunan Shi, Zhuoming Chen, Daiyaan Arfeen, Reyna Abhyankar, Zhihao Jia
    ASPLOS, July 2024
    arXiv
  3. DNSGuard: In-network Defense against DNS Attacks
    Guanglin Duan, Qing Li, Zhengxin Zhang, Dan Zhao, Guorui Xie, Yong Jiang
    IEEE TDSC, July 2024
    IEEE
  4. SeIoT: Smart Home Network Anomaly Detection via Knowledge Graph
    Qing Li, Ruoyu Li, Yucheng Huang, Qingsong Zou, Dan Zhao, Zhengxin Zhang, Yong Jiang
    IEEE TIFS, July 2024
    IEEE

2023

  1. Metis: Understanding and Enhancing Regular Expressions in Network
    Zhengxin Zhang*, Yucheng Huang*, Guanglin Duan*, Qing Li, Dan Zhao, Yong Jiang, Lianbo Ma, Xiao Xi, Hengyang Xu
    NeurIPS, Dec 2023
    OpenReview
  2. Pontus: Finding Waves in Data Streams
    Zhengxin Zhang, Qing Li, Guanglin Duan, Dan Zhao, Jingyu Xiao, Guorui Xie, Yong Jiang
    SIGMOD, June 2023
    ACM

* denotes equal contribution

Education

Cornell University

Ph.D. in Computer Science · Advisor: Prof. Claire Cardie

2024 — Present

Carnegie Mellon University

Visiting Scholar · Advisor: Prof. Zhihao Jia

2023 — 2024

Tsinghua University

M.S. in Computer Science and Engineering · GPA 3.88/4.0

2021 — 2024

Xidian University

B.S. in Software Engineering · GPA 3.86/4.0 · Rank 2/110

2017 — 2021

Experience

Carnegie Mellon University

Research Assistant · Advisor: Prof. Zhihao Jia

Machine learning systems and large language models

Jun 2023 — Aug 2024

Tencent, Shenzhen

Research Scientist Intern

XDP and eBPF algorithm design

Sep 2022 — Aug 2023

Awards

🏆
ACL Outstanding Paper Award, 2024
🎓
Outstanding Master Dissertation Award, Tsinghua University, 2024
🥇
First Prize Scholarship, Tsinghua University, 2022 & 2023
🥈
Second Place, Intel® P4 China Hackathon, 2022
🏅
Outstanding Graduates, Ministry of Education of Shaanxi Province
🎖️
Outstanding Student, Xidian University, 2018–2020
🇨🇳
National Scholarship, Ministry of Education of China, 2020
🏅
First Prize Scholarship, Xidian University, 2018 & 2019
📐
First Prize (top 0.036‰), China Undergraduate Mathematical Contest in Modeling, 2019
📐
First Prize, Xidian University Mathematical Modeling Contest, 2019
🌐
Meritorious Winner, International Mathematical Contest in Modeling, 2018

Talks

• Cornell NLP Seminar: Quantized Side Tuning: Fast and Efficient Tuning of Quantized Large Language Models. Sep 2024.

• Tencent: Regular Expressions in the Data Plane. Dec 2023.

Academic Service

• ICLR Reviewer 2025

• AAAI Programme Committee 2025

• NeurIPS Reviewer 2024, 2025

• COLM Reviewer 2025