About

Greetings! I am Qi Zeng (曾琪). I am currently a Senior Research Scientist on the Muse post-training team at Meta MSL (Meta Superintelligence Labs). I work hard so my cats Peanut Butter and Honey Butter can have a better life.

Work Experience

[LinkedIn]

• Meta MSL, Senior Research Scientist, 2024 - now
• ByteDance Seed, Research Scientist, 2024 - 2024
• Google DeepMind, Research Intern, 2023 Summer
• Amazon, Applied Scientist Intern, 2022 Summer
• Microsoft Research, Research Intern, 2021 Summer
• Allen Institute for Artificial Intelligence (AI2), Research Intern, 2020 Summer
• ByteDance AI Lab, Research Intern, 2019 Summer
• Microsoft Research Asia, Research Intern, 2018 Spring
• Microsoft, Machine Learning Engineer Intern, 2017 Spring

Education

University of Illinois Urbana-Champaign

• PhD in Computer Science, 2019 - 2023
• MS in Computer Science (on the way to PhD), 2019 - 2021
• Graduate Research Assistant at Blender Lab, Advisor: Prof. Heng Ji
• Research Focuses: Natural Language Processing (NLP), Information Extraction, Document Summarization

Peking University

• BS in Information Science, 2014 - 2018
• Freshman year in German Language and Literature, 2013 - 2014

Publications

[Google Scholar]. [DBLP]. [Semantic Scholar].

* means equal contribution.

• Sharpening Tax in Post-Training
  Changdae Oh, Qi Zeng, Qi Qi, Andrey Zhmoginov, Deren Lei, Yun He, Hoang Phan, Hangoo Kang, Azalia Mirhoseini, Sharon Li
  Arxiv
  [PDF] [Project]

• MIMESIS: Learning User Simulators as Training Environments for Interactive Agents
  Hoang Phan, Dat Huynh, Andrey Zhmoginov, Qi Zeng, Wancen Mu, Yue Cao, Shengjie Bi, Yun He, Changdae Oh, Deren Lei
  Arxiv
  [PDF]

• Automatic Prompt Engineering for Scalable Prompt Inversion in Text-to-Image Ad Generation
  Zixin Ding, Qi Zeng, Boying Gong, Wenlong Deng, Bo Pan, Yuxin Chen
  ACL 2026 Industry Track
  [PDF]

• Efficient Forward-Only Data Valuation for Pretrained LLMs and VLMs
  Wenlong Deng, Qi Zeng, Jiaming Zhang, Minghui Chen, Zixin Ding, Christos Thrampoulidis, Boying Gong, Xiaoxiao Li
  ACL 2026
  [PDF]

• Two-Step Offline Preference-Based Reinforcement Learning with Constrained Actions
  Yinglun Xu, Tarun Suresh, Rohan Gumaste, David Zhu, Ruirui Li, Zhengyang Wang, Haoming Jiang, Xianfeng Tang, Qingyu Yin, Monica Xiao Cheng, Qi Zeng, Chao Zhang, Gagandeep Singh
  Transactions on Machine Learning Research (TMLR)
  [PDF]

• SmartBook: AI-Assisted Situation Report Generation
  Revanth Gangi Reddy, Daniel Lee, Yi R. Fung, Khanh Duy Nguyen, Qi Zeng, Manling Li, Ziqi Wang, Clare Voss, Heng Ji
  Handbook on Neurosymbolic AI and Knowledge Graphs
  [PDF] [Code] [Demo]

• Scientific Opinion Summarization: Meta-review Generation with Checklist-guided Iterative Introspection
  Qi Zeng*, Mankeerat Sidhu*, Ansel Blume, Hou Pong Chan, Lu Wang, Heng Ji
  IJCAI 2024 (AI4Research Workshop)
  [PDF] [Code and Data]

• Improving Consistency for Text Summarization with Energy Functions
  Qi Zeng, Qingyu Yin, Zheng Li, Yifan Gao, Sreyashi Nag, Zhengyang Wang, Bing Yin, Heng Ji, Chao Zhang
  EMNLP 2023
  [PDF]

• Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning
  Yinglun Xu, Qi Zeng, Gagandeep Singh
  Transactions on Machine Learning Research (TMLR)
  [PDF] [Code]
  

• Interpretable Automatic Fine-grained Inconsistency Detection in Text Summarization
  Hou Pong Chan, Qi Zeng, Heng Ji
  ACL 2023
  [PDF] [Code]

• C-PMI: Conditional Pointwise Mutual Information for Turn-level Dialogue Evaluation
  Liliang Ren*, Mankeerat Sidhu*, Qi Zeng, Revanth Gangi Reddy, Heng Ji, Chengxiang Zhai
  ACL 2023 (DialDoc Workshop)
  [PDF]

• RESIN-11: Schema-guided Event Prediction for 11 Newsworthy Scenarios
  Xinya Du, Zixuan Zhang, Sha Li, Pengfei Yu, Hongwei Wang, Tuan Lai, Xudong Lin, Ziqi Wang, Iris Liu, Ben Zhou, Haoyang Wen, Manling Li, Darryl Hannan, Jie Lei, Hyounghun Kim, Rotem Dror, Haoyu Wang, Michael Regan, Qi Zeng, QING LYU, Charles Yu, Carl Edwards, Xiaomeng Jin, Yizhu Jiao, Ghazaleh Kazeminejad, Zhenhailong Wang, Chris Callison-Burch, Mohit Bansal, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Martha Palmer, Heng Ji
  NAACL 2022 (Demo Paper)
  [PDF] [Code]

• EA$^2$E: Improving Consistency with Event Awareness for Document-level Argument Extraction
  Qi Zeng*, Qiusi Zhan*, Heng Ji
  NAACL 2022
  [PDF] [Code]

• Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences
  Yifan Chen*, Qi Zeng*, Dilek Hakkani-Tur, Di Jin, Heng Ji, Yun Yang
  NAACL 2022
  [PDF] [Code]

• Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr"om Method
  Yifan Chen*, Qi Zeng*, Heng Ji, Yun Yang
  NeurIPS 2021
  [PDF] [Code] [Poster] [Appendix]

• GENE: Global Event Network Embedding
  Qi Zeng, Manling Li, Tuan Lai, Heng Ji, Mohit Bansal, Hanghang Tong
  NAACL 2021 (TextGraphs-15 Workshop)
  [PDF] [Code]

• GAIA at SM-KBP 2020 - A Dockerlized Multi-media Multi-lingual Knowledge Extraction, Clustering, Temporal Tracking and Hypothesis Generation System
  Manling Li, Ying Lin, Tuan Manh Lai, Xiaoman Pan, Haoyang Wen, Lifu Huang, Zhenhailong Wang, Pengfei Yu, Di Lu, Qingyun Wang, Haoran Zhang, Qi Zeng, Chi Han, Zixuan Zhang, Yujia Qin, Xiaodan Hu, Nikolaus Parulian, Daniel Campos, Heng Ji, Alireza Zareian, Hassan Akbari, Brian Chen, Bo Wu, Emily Allaway, Shih-Fu Chang, Kathleen McKeown, Yixiang Yao, Jennifer Chen, Eric Berquist, Kexuan Sun, Xujun Peng, Ryan Gabbard, Marjorie Freedman, Pedro Szekely, T.K. Satish Kumar, Arka Sadhu, Haidong Zhu, Ram Nevatia, Miguel Rodriguez, Yifan Wang, Yang Bai, Ali Sadeghian, Daisy Zhe Wang
  TAC 2020 (Text Analysis Conference)
  [PDF]

• ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis
  Qingyun Wang, Qi Zeng, Lifu Huang, Kevin Knight, Heng Ji, Nazneen Fatema Rajani
  INLG 2020
  [PDF] [Code]

• Connecting the Dots: Event Graph Schema Induction with Path Language Modeling
  Manling Li, Qi Zeng, Ying Lin, Kyunghyun Cho, Heng Ji, Jonathan May, Nathanael Chambers, Clare Voss
  EMNLP 2020
  [PDF] [Code]

• Cross-media Structured Common Space for Multimedia Event Extraction.
  Manling Li*, Alireza Zareian*, Qi Zeng, Spencer Whitehead, Di Lu, Heng Ji, Shih-Fu Chang
  ACL 2020
  [PDF] [Code]

• LexicalAT: Lexical-Based Adversarial Reinforcement Training for Robust Sentiment Classification
  Jingjing Xu, Liang Zhao, Hanqi Yan, Qi Zeng, Yun Liang, Xu Sun
  EMNLP 2019
  [PDF] [Code]

• Asking Clarification Questions in Knowledge-Based Question Answering
  Jingjing Xu, Yuechen Wang, Duyu Tang, Nan Duan, Pengcheng Yang, Qi Zeng, Ming Zhou, Xu Sun
  EMNLP 2019
  [PDF] [Code]

• Review-Driven Multi-Label Music Style Classification by Exploiting Style Correlations
  Jingjing Xu*, Guangxiang Zhao*, Qi Zeng, Xuancheng Ren, Xu Sun
  NAACL 2019
  [PDF] [Code]

• Text Assisted Insight Ranking Using Context-Aware Memory Network
  Qi Zeng*, Liangchen Luo*, Wenhao Huang, Yang Tang
  AAAI 2019
  [PDF] [Poster]

• Learning Personalized End-to-End Goal-Oriented Dialog
  Liangchen Luo, Wenhao Huang, Qi Zeng, Xu Sun, Zaiqing Nie
  AAAI 2019
  [PDF] [Poster]

• An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation
  Jingjing Xu*, Liangchen Luo*, Junyang Lin, Qi Zeng, Xu Sun
  EMNLP 2018
  [PDF] [CODE] [Poster]

• A Skeleton-Based Model for Promoting Coherence in Narrative Story Generation
  Jingjing Xu, Xuancheng Ren, Yi Zhang, Qi Zeng, Xiaoyan Cai, Xu Sun
  EMNLP 2018
  [PDF] [CODE]

• Unpaired Sentiment-to-Sentiment Translation Using Cycled Reinforcement Learning
  Jingjing Xu, Xu Sun, Qi Zeng, Xuancheng Ren, Xiaodong Zhang, Houfeng Wang, Wenjie Li
  ACL 2018
  [PDF] [CODE] [SLIDES]