I am a fourth-year Ph.D. candidate in the Department of Computer Science and Engineering at the State University of New York at Buffalo, where I am fortunate to be advised by Prof. Jinjun Xiong. Prior to this, I earned my M.S. in Statistics from the University of Illinois at Urbana-Champaign in 2022 and my B.S. in Mathematics from Central South University (China) in 2020.

I am actively seeking a summer internship for 2026 and part-time opportunities available at any time.

Research

My research focuses on the intersection of optimization for large language models and the theoretical foundations of machine learning. My major research focuses include:

LLMs Post-training (Preference Optimization and Parameter Efficient Fine-Tuning)

Multi-agent System Design and Application

Efficient LLMs Optimizer (Pre-training and Post-training)

Hierarchical Optimization (Minimax and Bilevel Optimization)

Federated Learning and Communication Networks

Publications

Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis.

         Yifan Yang, Hao Ban, Minhui Huang, Shiqian Ma, Kaiyi Ji.
         [ICLR 2025]

First-Order Federated Bilevel Learning.

         Yifan Yang, Peiyao Xiao, Shiqian Ma, Kaiyi Ji.
         [AAAI 2025]

First-Order Minimax Bilevel Optimization.

         Yifan Yang*, Zhaofeng Si*, Siwei Lyu, Kaiyi Ji.
         [NeurIPS 2024]

SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning.

         Yifan Yang, Peiyao Xiao, Kaiyi Ji.
         [NeurIPS 2023 (Spotlight, 3% Acceptance)]

Achieving O(\epsilon^{-1.5}) Complexity in Hessian-free Stochastic Bilevel Optimization.

         Yifan Yang, Peiyao Xiao, Kaiyi Ji.
         [NeurIPS 2023]

Imperative Learning: A Self-supervised Neural-Symbolic Learning Framework for Robot Autonomy.

         Chen Wang, Kaiyi Ji, Junyi Geng, Zhongqiang Ren, ..., Yifan Yang, Xiao Lin, Zhipeng Zhao.
         [IJRR]

Experiences

AI Research Intern, SAP (May 2025 – Nov 2025)

Talks

Glad to give an invited talk at INFORMS Optimization Society 2024 (Rice University, Houston, TX).

Service

I served as a conference reviewer of:

ICML 2025, 2026

ICLR 2024, 2025, 2026

NeurIPS 2024, 2025

AAAI 2026

AISTATS 2025, 2026

ACML 2024

I served as a journal reviewer of:

Journal of Machine Learning Research

IEEE Transactions on Signal Processing

SIAM Journal of Optimization

Mathematics

Fractal and Fract

IEEE Transactions on Circuits and Systems for Video Technology

Teaching Experiences

I worked as a teaching assistant of the following courses:

CSE676: Deep Learning (2024 Spring)

CSE431/531: Algorithm Analysis and Design (2023 Fall)

CSE460/560: Data Models and Query Languages (2023 Spring)