Zhining Liu
GitHub followers Zhihu followers Xiaohongshu profile Bilibili followers Steam friends

Zhi-ning Liu

你好 / Hello / 안녕하세요 / こんにちは / Bonjour / Hola (and more)!

Applied Scientist @ Amazon
Ph.D. @ University of Illinois Urbana-Champaign (UIUC)

Building agentic, self-improving AI systems to automate industrial R&D at scale. More broadly, my research spans reliable LLM and VLM reasoning, automated data engineering and data mining. Published 30+ papers at leading venues with 1,000+ citations. Alongside these efforts, I build and maintain research-driven open-source software and projects with 4K+ GitHub stars and 200K+ downloads.

CV Email Scholar GitHub LinkedIn Zhihu
Agentic & Self-Improving AI
  • Agent Harness (, )
  • Agentic Reasoning & Planning (, )
  • Self-Improving Agents (, )
Reliable LLM & VLM Reasoning
  • Long-Context Reasoning (, )
  • Multimodal Grounding (, )
  • Safety & Alignment (, , )
Data-Centric AI
  • Data Optimization (, , )
  • Data Interpretability (, , )
  • Long-Tail Learning (, , )
Automated Data Mining
  • Model Fusion (, , )
  • Time Series (, , )
  • Graph Learning (, )

News

Aug 2026
🎓 Ph.D. unlocked! Successfully defended on August 21st : )
Aug 2026
🎉 EMNLP'26: ReContext accepted to EMNLP 2026. [PDF/Code]
Jul 2026
🎉 COLM'26: 2 papers accepted to COLM 2026.
May 2026
🏆 Award: 2026 C.W. Gear Outstanding Graduate Student (1 in UIUC CS Dept.).
May 2026
🔥 HF Daily #1 Paper: Code as Agent Harness! [HF/GitHub]
May 2026
🎉 ICML'26: One paper accepted to ICML 2026.
Apr 2026
🎉 ACL'26: 3 papers (2 Main, 1 Findings) accepted to ACL 2026.
Jan 2026
🔥 HF Week #1 Paper: All you need to know about Agentic Reasoning! [HF/GitHub]
Jan 2026
🇧🇷 ICLR'26: 4 papers accepted to ICLR 2026. See you in Brazil!
Jan 2026
🌟 WWW'26 Oral: One paper accepted to WWW 2026 as an oral presentation. [PDF/Code]
Oct 2025
👀 VLM Perception: VLMs can see the image, but still may not use it. [PDF]
Sep 2025
📊 NeurIPS'25: One paper on benchmarking class-imbalanced tabular learning accepted to NeurIPS 2025. [Code/PDF]
Aug 2025
🎉 EMNLP'25: One Findings paper accepted to EMNLP 2025. [PDF/Code]
Aug 2025
🎉 CIKM'25: One paper accepted to CIKM 2025. [PDF/Code]
Jul 2025
🎉 RecSys'25: LLM-RecG accepted to RecSys 2025. [PDF/Code]
May 2025
🏆 Award: Honored to receive the 2025 C.L. and Jane Liu Award! (2 in UIUC CS Dept.) (school website)
May 2025
🔎 ACL'25: How to prevent LLMs from overlooking the evidence in your RAG? [Code/PDF]
May 2025
📈 ICML'25: Sample-level adaptive model fusion for time series forecasting. [Code/PDF]
May 2025
💼 Intern@Amazon: Back to the Bay Area again.
Jan 2025
🎉 ICLR'25: One paper on test-time adaptation for graph structural shift accepted. [PDF]
Sep 2024
🌟 NeurIPS'24 Spotlight: One paper on time-series backdoor attacks accepted. [Code/PDF]
May 2024
⚖️ KDD'24: AIM: Attributing, Interpreting, Mitigating Data-encoded Unfairness. [Code/PDF]
May 2024
💼 Intern@Amazon: Starting my Applied Scientist Internship in the Bay Area.
Apr 2024
🧩 ICML'24: Class-imbalanced graph learning without class rebalancing? [Code/PDF]
Mar 2024
⚖️ FAccT'24: Group Fairness via Group Consensus, with Eunice Chan. [PDF]
May 2023
🏥 KDD'23: Web-based Long-term Spine Treatment Outcome Forecasting, with Hangting Ye. [PDF]
May 2023
💼 Intern@Amazon: Starting my Applied Scientist Internship in Seattle.
Feb 2023
📦 Open-source: Major release of IMBENS, an imbalanced learning toolbox. [GitHub/Docs/PyPI]
Feb 2023
🔬 ICDE'23: UADB: Unsupervised Anomaly Detection Booster, with Hangting Ye. [Code/PDF]
Mar 2022
🎓 Starting Ph.D.@UIUC: I will join Prof. Hanghang Tong's group at UIUC in Fall 2022.
Jan 2022
📦 Open-source: Awesome2ML, a curated list across machine learning topics. [ENG/中文]
Nov 2021
📝 Preprint: IMBENS: Ensemble Class-imbalanced Learning in Python. [Code/PDF]
Jun 2021
📦 Open-source: IMBENS, an imbalanced learning toolbox. [GitHub/Docs/PyPI]
Oct 2020
🧠 NeurIPS'20: MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler. [Code/PDF]
Apr 2020
📦 Open-source: Awesome-Imbalanced-Learning, a curated list of imbalanced learning resources.
Oct 2019
🔬 ICDE'20: Self-paced Ensemble for Highly Imbalanced Massive Data Classification. [Code/PDF]
Jul 2019
🎓 Graduation@JilinU: Received my B.Sc. from Tang Aoqing Honors Program in Science, Jilin University.
Sep 2018
💼 Intern@Microsoft: Starting my internship at Microsoft Research Asia. Supervisors: Dr. Jiang Bian and Dr. Wei Cao.

Education

University of Illinois Urbana-Champaign

Ph.D. in Computer Science · 2022 - 2026
Department of Computer Science · Advisor: Prof. Hanghang Tong

Jilin University

M.Eng. in Computer Science · 2019 - 2022
School of Artificial Intelligence · Advisor: Prof. Yi Chang
B.Sc. in Computer Science · 2015 - 2019
Tang-Aoqing Honors Program (Top ~0.5% at matriculation)

Experience

Amazon

Applied Scientist, Palo Alto, CA, Jul 2026 - Present
Self-improving agent harness for industrial R&D at scale.
Applied Scientist Internships
2025, Palo Alto, CA (8 months): Reliable VLM Reasoning -> , ,
2024, Palo Alto, CA (4 months): RAG-Enhanced LLM Reasoning ->
2023, Seattle, WA (4 months): User query understanding

Microsoft Research

Research Intern, Beijing, Aug 2018 - June 2019 (9 months)
Extreme class-imbalanced learning -> ,

Publications

Publications, preprints, and submissions, sorted by year. See the full list on Google Scholar.

Awards & Honors

  1. C.W. Gear Outstanding Graduate Student

    University of Illinois Urbana-Champaign

    Top 0.2%*1 recipient in UIUC CS department

  2. C.L. and Jane Liu Award

    University of Illinois Urbana-Champaign

    Top 0.3%*2 recipients in UIUC CS department

  3. Top 10 Graduate Student (University Highest Honor)

    Jilin University

    Top 0.04%*10 of 28,373 graduate students

  4. National Scholarship

    Ministry of Education of China

    Top 0.2%Nationwide

  5. National Scholarship

    Ministry of Education of China

    Top 0.2%Nationwide

* Estimated using official enrollment data at the time: UIUC CS PhD students (644); Jilin University graduate students (28,373).

Fun Facts

🌿 My Name
In Chinese, "Zhi Ning" has a gently feminine feeling: Zhi (芷) means fragrant herb, and Ning (宁) means peace and tranquility. Because of this name, some friends once expected to meet a cute girl before seeing me in person, and were mildly disappointed when reality arrived.
🎮 Games
I enjoy nearly every kind of video game, although I am not necessarily good at them: shooters, strategy, 4X, role playing games, roguelikes, racing games, and more. Some of my favorites include Battlefield, Civilization, Stellaris, GTA, The Witcher, DiRT, Homeworld, Metro, BioShock, and Borderlands.
🎨 Making Things
Making things look nice and organized makes me happy. That's why I make good paper figures, tables, and website. I also have a sleek desktop setup. In another life, I might be a designer or a professional organizer. Unfortunately, the former may soon be replaced by AI, while the latter probably still has some time.