About

Hello! I am Yan Li (李岩), an incoming phd student with Prof. Sean Du to NTU.

Previously, I obtained master degree in Machine Learning at the Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), advised by Prof. Kun Zhang. I work closely with Guangyi Chen and Yunlong Deng in the MBZUAI Causality Group.

From July 2025 to December 2025, I was a visiting student in the Department of Philosophy at Carnegie Mellon University (CMU), working with Prof. Peter Spirtes and Prof. Kun Zhang, and collaborating with the CMU CLeaR Group. I obtained a B.Eng. in Computer Science and Technology from Tsinghua University in June 2024, where I worked at the Research Institute of Human–Computer Interaction and Media Integration with Chun Yu, mainly on HCI and context-aware systems.

Broadly, I am interested in the mathematical and causal foundations of machine learning, and in building robust and interpretable models.

Research interests

• Causal representation learning
• Domain adaptation, domain generalization, and out-of-distribution robustness
• Multimodal and vision–language models

News

• 2026.01 - “Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens” accepted to ICLR 2026 (poster).
• 2025.12 — I will attend NeurIPS 2025 in San Diego and present two posters. Feel free to talk to me at the poster sessions.
• 2025.09 — “CausalVerse: Benchmarking Causal Representation Learning with Configurable High-Fidelity Simulations” accepted to NeurIPS 2025 (spotlight).
• 2025.09 — “Towards Self-Refinement of Vision-Language Models with Triangular Consistency” accepted to NeurIPS 2025 (poster).
• 2025.04 — “A General Representation-Based Approach to Multi-Source Domain Adaptation” presented at ICML 2025 (poster).
• 2025.07–2025.12 — Visiting student at Carnegie Mellon University, Department of Philosophy.
• 2024.10 — Started the M.Sc. in Machine Learning at MBZUAI, advised by Kun Zhang.
• 2024.06 — Graduated from Tsinghua University (B.Eng. in Computer Science and Technology).
• 2023.06–2023.07 — Research intern at Mian Bi Intelligent Technology Co., Ltd., working on pre-training data preparation for large language models.
• 2022 — Third Prize, 40th Challenge Cup of Tsinghua University.
• 2020 — Second-Class Scholarship for Freshmen, Tsinghua University.

Publications

Equal contribution is indicated by * after author names.

Featured paper

CausalVerse: Benchmarking Causal Representation Learning with Configurable High-Fidelity Simulations Guangyi Chen*, Yunlong Deng*, Peiyuan Zhu*, Yan Li*, Yifan Shen, Zijian Li, Kun Zhang. NeurIPS 2025 Datasets and Benchmarks Track, Spotlight. [Paper] [Project Page]

Full papers

• A Dialogue between Causal and Traditional Representation Learning: Toward Mutual Benefits in a Unified Formulation
  Yan Li, Yuewen Sun, Shaoan Xie, Gongxu Luo, Yunlong Deng, Kun Zhang, Guangyi Chen.

• Multimodal LLMs under Pairwise Modalities
  Yan Li*, Yunlong Deng*, Yuewen Sun, Gongxu Luo, Kun Zhang, Guangyi Chen.

• Should Bias Always Be Eliminated? A Principled Framework to Use Data Bias for OOD Generation
  Yan Li, Yunlong Deng, Zijian Li, Anpeng Wu, Zeyu Tang, Kun Zhang, Guangyi Chen.

• Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens
  Yunlong Deng, Boyang Sun, Yan Li, Zeyu Tang, Lingjing Kong, Kun Zhang, Guangyi Chen.
  ICLR 2026, Poster.

• Towards Self-Refinement of Vision-Language Models with Triangular Consistency
  Yunlong Deng, Guangyi Chen, Tianpei Gu, Lingjing Kong, Yan Li, Zeyu Tang, Kun Zhang.
  NeurIPS 2025, Poster.

• A General Representation-Based Approach to Multi-Source Domain Adaptation
  Ignavier Ng*, Yan Li*, Zijian Li, Yujia Zheng, Guangyi Chen, Kun Zhang.
  ICML 2025, Poster.

• ProtoGS: Efficient and High-Quality Rendering with 3D Gaussian Prototypes
  Zhengqing Gao, Dongting Hu, Jia-Wang Bian, Huan Fu, Yan Li, Tongliang Liu, Mingming Gong, Kun Zhang.

• Revealing Personalized Positions in Indoor Spaces: A User-Centric Approach to Context-Aware Area Discovery
  Zhaoheng Li, Chun Yu, Yan Li, Yuanchun Shi.
  Undergraduate work on human–computer interaction and context-aware area discovery.

Industry experience

Mian Bi Intelligent Technology Co., Ltd. · Jun. 2023 – Jul. 2023
Supervisor: Jie Cai, Algorithm Engineer

• Worked on data preparation for pre-training large language models, including data-cleaning algorithms and large-scale batch cleaning.
• Participated in discussions on classical text LLMs, data pipelines, and preliminary design.

Education

• M.Sc. in Machine Learning, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · Oct. 2024 – Jun. 2026
  Supervisor: Kun Zhang

• Visiting student, Department of Philosophy, Carnegie Mellon University (CMU) · Jul. 2025 – Dec. 2025
  Visiting tutors: Peter Spirtes, Kun Zhang

• B.Eng. in Computer Science and Technology, Tsinghua University · Sept. 2020 – Jun. 2024

Honors and awards

• MBZUAI Conference Travel Scholarship, 2025
• Tsinghua University Academic Progress Scholarship, 2023
• Social Practice Excellence Scholarship of Tsinghua University, 2022
• Third Prize, 40th Challenge Cup of Tsinghua University, 2022
• Second-Class Scholarship for Freshmen, Tsinghua University, 2020

Service

• Reviewer: ICLR, ICML, NeurIPS

Contact

• Email: lyan012010 (at) gmail (dot) com