I am currently pursuing my Ph.D. at the CAS Key Laboratory of AI Safety, advised by Prof. Xueqi Cheng and Assoc. Prof. Bingbing Xu. I obtained my B.S. degree in Information Security from Xidian University in 2020.

My research goal is to build Trustworthy AI that performs reliably across diverse scenarios. To achieve this, I worked on Generalization & Robustness and Alignment & Hallucination within domains of graph, vision, and language, for tasks of both discriminative and generative modeling.

🔥 News

📝 Selected Publications [FullList]

ICLR 2025
sym

SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters

Teng Xiao*, Yige Yuan*, Zhengyu Chen, Mingxiao Li, Shangsong Liang, Zhaochun Ren, Vasant G Honavar

(Paper)(Code)(Slides)(Poster)

ICLR 2025
sym

On a Connection Between Imitation Learning and RLHF

Teng Xiao, Yige Yuan, Mingxiao Li, Zhengyu Chen, Vasant G Honavar

(Paper)(Code)(Slides)(Poster)

CVPR 2024
sym

TEA: Test-time Energy Adaptation

Yige Yuan, Bingbing Xu, Liang Hou, Fei Sun, Huawei Shen, Xueqi Cheng

  • We propose to investigate generalization from an energy-based perspective and introduce TEA, a test-time adaptation method which transforms the trained classifier into an energy-based model and aligns the model’s distribution with the test data’s, enhancing its ability to perceive test distributions and thus improving overall generalizability.

(Paper)(Code)(Slides)(Poster)

AAAI 2024
sym

PDE+: Enhancing Generalization via PDE with Adaptive Distributional Diffusion

Yige Yuan, Bingbing Xu, Bo Lin, Liang Hou, Fei Sun, Huawei Shen, Xueqi Cheng

  • We propose to investigate generalization from PDE perspective and propose PDE-ADD framework. We introduce adaptive distributional diffusion into transport equation to enhance smoothness of its solution, thereby improving generalization directly via the underlying function of NN.

(Paper)(Code)(Slides)(Poster)

Neural Networks
sym

Towards Generalizable Graph Contrastive Learning: An Information Theory Perspective

Yige Yuan, Bingbing Xu, Huawei Shen, Qi Cao, Keting Cen, Wen Zheng, Xueqi Cheng

  • We propose a GCL generalization ability metric and prove a MI upper bound for it from an information-theoretic perspective. Guided by the bound, we design an InfoAdv framework, which can be applied to current GCL models and achieves SOTA performance.

(Paper)(Code)(Slides)(Poster)

🎖 Awards && Honors

  • 2025 First place, AgentSociety Challenge @ WWW 2025
  • 2024 National Scholarship (Doctoral Students)
  • 2024 First-Class Scholarship, University of Chinese Academy of Sciences
  • 2023 Presidential Scholarship, Institute of Computing Technology
  • 2022 First-Class Scholarship, University of Chinese Academy of Sciences
  • 2022 Outstanding Student Award, University of Chinese Academy of Sciences
  • 2019 First Prize, 12th National College Students Information Security Contest
  • 2017 First Prize, 15th National Science and Technology Academic Competition of Challenge Cup

🧳 Experiences

  • 2025.01 - Present, Tongyi Lab, Alibaba Group.
    • Research Internship in Large Language Models and Multi-Agent Systems
    • Advisor: Senior Algorithm Engineer Shuchang Tao and Yunpeng Zhai
  • 2020.09 - Present, Institute of Computing Technology, Chinese Academy of Seiences.
  • 2016.09 - 2020.06, Xidian University.
    • Department of Network and Information Security
    • B.S. in Information Security (Experimental Class)

💻 Invited Talks

  • NICE Webinar, On a Connection Between Imitation Learning and RLHF, March 2025 [video]
  • AITime Youth PhD Talk, On a Connection Between Imitation Learning and RLHF, March 2025 [video]
  • LOGS Webinar, Partial Differential Equation-Driven Generalizable Neural Networks, March 2024 [video]
  • AITime Webinar, TEA: Test-time Energy Adaptation, April 2024
  • WizSci Webinar, PDE+: Enhancing Generalization via PDE with Adaptive Distributional Diffusion, Jan 2024

🎓 Academic Services

  • Conference Reviewers: NeurIPS (2024, 2025), ICML 2025, ICLR 2025, AISTATS 2025, KDD 2025, WWW 2025, AAAI 2025, IJCAI 2025, ACL 2025, EMNLP 2024, COLING 2025, ACL Rolling Review, MIDL 2025, IJCNN 2025

  • Journal Reviewers: IEEE Transactions on Knowledge and Data Engineering (TKDE), Applied Intelligence (APIN)