Zifeng Wang

I am a Research Scientist at Google Cloud AI Research, focusing on large language models (LLMs) and their applications. My research interests span self-improving agents, environment scaling, and agentic post-training. I received my PhD in Machine Learning from Northeastern University's SPIRAL Group, advised by Prof. Jennifer G. Dy.

Prior to my PhD, I earned my BS in Electronic Engineering from Tsinghua University, where I worked on computer vision with Prof. Jiwen Lu (Tsinghua) and Prof. Jia Deng (Princeton), and big data with Prof. Yong Li (Tsinghua).

I am looking for self-motivated student researchers / research interns with interests and expertise in LLMs! Feel free to contact me if you would like to work on cutting-edge challenges in machine learning and LLMs.

Email  /  Google Scholar  /  LinkedIn  /  Twitter  /  CV

• Large Language Models
• Self-improving (multi-)agents
• Environment scaling for agent learning
• Agentic post-training
• Synthetic data for post-training and evaluation
• Cost-effective LLM inference (e.g., Routing, Distillation)
• Continual (Lifelong) Learning
• Open Set Recognition / Novel Class Discovery
• Adversarial Robustness and Model Compression

• 
  Aug 2023 - Present, Google,
  Research Scientist at Cloud AI Research
• 
  Sep 2018 - Jul 2023, Northeastern University,
  Research Assistant at SPIRAL Group
• 
  Jun 2021 - Jan 2023, Google,
  Student Researcher / Research Intern at Cloud AI Research
• 
  Feb 2017 - Jul 2018, Tsinghua University,
  Research Assistant at i-Vision Group
• 
  Jul 2017 - Sep 2017, University of Michigan,
  Visiting Researcher at Vision & Learning Lab

• EnvHarness: Awakening Static Worlds for Agent Learning
  - COLM'26 Google Expo, 2026, San Francisco, California
  - ServiceNow Research and Mila, 2026, Remote
• Automated Multi-Agent System Optimization
  - Google DeepMind, 2025, Remote
• CodecLM: Synthetic Data Generation for Large Language Models
  - Google Cloud, 2024, Remote
• Effective and Efficient Continual Learning
  - CFAR, A*STAR, 2023, Remote
• Sparse Continual Learning on the Edge
  - ContinualAI, 2023, Remote
  - AI Time, 2023, Remote (Chinese version)
• Prompting-based Continual Learning
  - AI Talks SG, 2022, Remote
  - ContinualAI, 2022, Remote [recording]
• Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness
  - INFORMS Annual Meeting, 2022, Indianapolis, Indiana [abstract]
  - AI Time, 2022, Remote (Chinese version) [recording][blog]

• Outstanding Student Award in Research, Northeastern University, 2023
  
• Scholar Award, NeurIPS 2022
  
• Best Paper Candidate, ICDM 2020
  
• Best Paper Award, DySPAN 2019
  
• Dean's Fellowship, Northeastern University, 2018
     Highest honor awarded to new PhD students for outstanding academic background.
• Evergrande Scholarship, Tsinghua University, 2016
     Awarded to students with excellent academic performance, scientific potential and overall development.

Area Chair: ACL ARR
Conference Reviewer: NeurIPS, ICML, ICLR, CVPR, ICCV
PC Member: SDM
Journal Reviewer: TPAMI, TMLR, Neural Networks