Shaobo Cui

Welcome to my homepage! I am Shaobo Cui, a fourth-year PhD student in Computer Science at EPFL. I have the privilege of being supervised by Prof. Boi Faltings (AAAI and EurAI Fellow), with co-supervision from Prof. Antoine Bosselut and mentorship by Prof. Michael C. Gastpar.

My research focuses on causal reasoning, causality for science, and human-computer interaction. Along the way, my work has been recognized with prestigious honors including the Rising Star Award (明日之星) from Alibaba Group (2020) and the DAAD AInet Fellow in AI for Science Track (2024). My work has also resulted in 9 patents for industrial applications.

Before embarking on my doctoral journey, I worked as a full-time Senior Research Engineer at DAMO Academy, Alibaba Group: I led projects in human-computer interaction, natural language processing, and recommendation algorithms for digital humans. Notably, I developed the recommendation algorithm for Alibaba’s Virtual Influencer from 0 to 1, showcased at the Winter Olympic Games, Beijing 2022.

Research Highlight: Human-Computer Interaction

I am passionate about empowering machines to better understand and engage with humans. Below are key areas of contribution:

• Industrial Human-Computer Interaction Systems:
  • Enhanced retrieval-based dialogue systems using session information (CIKM 2020, KDD 2020), with related [patents].
  • Advanced generative dialogue techniques using frameworks such as MTSS (AAAI 2020) and DAL (NeuGen).
  • Optimized response timing in dialogue systems (TASLP 2021).
  • Developed a one-stop approach for knowledge extraction (WWW 2021).
  • Pioneered methods for automated dialogue system testing (patents).
• Virtual Influencers:
  • Built the recommendation algorithm for Alibaba’s Virtual Influencer from scratch, leading to its debut at the Beijing 2022 Winter Olympics.
  • Applied generative AI techniques to assist virtual influencers in manuscript creation (CIKM 2021).
• Machine Learning & Optimization:
  • Innovations in optimization methods like greedy coordinate descent, regularized optimal transport, and Lipschitz-constrained WGAN (NeurIPS 2017, ICTAI 2017).
• Communication Enhancement:
  • Improved heading designs in academia, SEO, and advertising by balancing summarization, creativity, and algorithmic structuring (ACL Findings 2024, nominated as a Best Paper Candidate⭐).

Research Highlight: Causal Reasoning and Causality for Science

My Ph.D. thesis explores innovative ways to advance machine understanding of causality, focusing on the following key areas:

• Commonsense Causality:
  • Synthesized insights on benchmarks, acquisition, and reasoning methods for commonsense causality under a novel taxonomy (EMNLP 2024).
• Defeasibility in Causal Reasoning:
  • Introduced and quantified defeasibility, a critical but often overlooked aspect of causality (ACL Findings 2024).
• Consistency in Causal Reasoning for LLMs:
  • Explored whether large language models maintain self-consistency over nuanced causality (AAAI 2025).
• Causality for Science:
  • Ongoing research to leverage causality for advancing scientific discovery, with results forthcoming.

Research Highlight: Open-Source Software

I actively contribute to the open-source community, developing tools that help advance research and real-world applications in natural language processing and machine learning.

• fancy-title: Python package for evaluating and optimizing titles in academia, SEO, and more.
• causal-strength: Python package for measuring and visualizing causal strength.

Patents 📑

I have contributed to 9 patents in AI, machine learning, and human-computer interaction systems, focusing on model training, human-computer interaction, and data processing. Highlights include:

• Cui, Shaobo; Lian, Rongzhong; Jiang, Di; He, Jingzhou. 2018. “Training method and device as well as computer equipment and readable storage medium.” CN108846124B, filed on June 29, 2018, and granted on May 17, 2022.
• Ji, Feng; Peng, Shuke; Cui, Shaobo; Chen, Haiqing. 2020. “Network model obtaining method and device, information processing method and device and electronic equipment.” CN113450786B, filed on March 25, 2020, and granted on July 26, 2024.
• Cui, Shaobo; Ji, Feng; Tang, Dahuai, Kang Xiaoming. 2020. “Dialogue system testing method and device and statement rewriting method.” CN113742461B, filed on May 28, 2020, and granted on January 10, 2025.
• Kang, Xiaoming; Cui, Shaobo; Ji, Feng. 2020. “A man-machine interaction dialogue method and device.” CN113901181A, filed on July 6, 2020. Patent Pending.
• Fu, Zhenxin; Cui, Shaobo; Ji, Feng; Yan, Rui; Zhang, Ji; Chen, Haiqing. 2020. “Dialogue method and system.” CN114036267A, filed on July 21, 2020. Patent Pending.
• Cui, Shaobo; Ji, Feng; Lin, Zehao; Zhao, Zhongzhou; Chen, Haiqing; Zhang, Yin. 2020. “Dialogue model training method, dialogue method and dialogue device.” CN114254086A, filed on September 25, 2020. Patent Pending.
• Cui, Shaobo; Zu, Xinxing; Bao, Xintong; Zhao, Zhongzhou; Zhang, Ji; Chen, Haiqing. 2021. “A question-answer pair generation method, device, electronic device, and computer storage medium” CN115114416A, filed on March 23, 2021. Patent Pending.
• Cui, Shaobo; Fu, Zhenxin; Ji, Feng; Yan, Rui; Zhao, Zhongzhou; Chen, Haiqing. 2021. “Data processing method, device, electronic equipment and computer storage medium” CN115129831A, filed on March 29, 2021. Patent Pending.
• Cui, Shaobo; Tang, Dahuai; Zhao, Zhongzhou; Zhang,Ji; Chen, Haiqing. 2021. “Inquiry statement rewriting method and device.” CN113673256B, filed on July 21, 2021 and granted on August 27, 2024.

For Prospective Students

I have reserved time slots to supervise master students for thesis and semester projects. Undergraduate and master’s students interested in research projects are encouraged to read this page for more information. Feel free to drop me an email via myfirstname.mylastname[at]epfl.ch