About Me
I’m a PhD candidate at Purdue University under the supervision of Prof. Ananth Grama. I’m fortunate to also work with Prof. Zhangyang Wang and Prof. Junyuan Hong. Prior to my PhD, I completed my undergraduate studies in Electronic Information Engineering with a minor in Artificial Intelligence at the University of Science and Technology of China, where I fostered my curiosity and passion for research.
Research interests
- LLM post-training, particularly synthetic data generation, mechanism understanding and model self-improvement.
- LLM training and inference efficiency
- Trustworthy ML
NEWS
- Jan, 2026. One Paper accepted to ICLR 2026
- Nov, 2025. Our recent paper, LLMs Can Get “Brain Rot”!, has received widespread international media coverage, including features in Nature, Wired, Forbes, Fortune, The Chosun Daily (조선일보), India Today, Synced (机器之心), and others.
- Aug, 2025. One paper accepted to ACM-BCB 2025.
- July, 2025. Two papers accepted to COLM 2025.
- May, 2025. One paper accepted to ICML 2025.
- May, 2024. I’m thrilled to start my internship at Texas Instrument!
- May, 2024. One paper accepted to ICML 2024 (spotlight 3.5%) !
- Apr, 2023. One paper accepted to ICML 2023.
Publication List
DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning
Yifan Wang, Bolian Li, Junlin Wu, Zhaoxuan Tan, Zheli Liu, Ruqi Zhang, Ananth Grama, Qingkai Zeng
International Conference on Learning Representations (ICLR), 2026
LLMs Can Get “Brain Rot”!
Shuo Xing*, Junyuan Hong*, Yifan Wang, Runjin Chen, Zhenyu Zhang, Ananth Grama, Zhengzhong Tu, Zhangyang Wang
From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications
Ajay Jaiswal*, Yifan Wang*, Lu Yin, Shiwei Liu, Runjin Chen, Jiawei Zhao, Ananth Grama, Yuandong Tian, Zhangyang Wang
International Conference on Machine Learning (ICML), 2025
More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment
Yifan Wang, Runjin Chen, Bolian Li, David Cho, Yihe Deng, Ruqi Zhang, Tianlong Chen, Zhangyang Wang, Ananth Grama, Junyuan Hong
Conference on Language Modeling (COLM), 2025
Cascade reward sampling for efficient decoding-time alignment
Bolian Li*, Yifan Wang*, Ananth Grama, Ruqi Zhang
Conference on Language Modeling (COLM), 2025
Deconvolving Complex Neuronal Networks into Interpretable Task-Specific Connectomes
Yifan Wang, Vikram Ravindra, Ananth Grama
ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB), 2025
A Theory of Fault-Tolerant Learning
Changlong Wu, Yifan Wang, Ananth Grama
International Conference on Machine Learning (ICML), 2024 (Spotlight 3.5%)
Learning Functional Distributions with Private Labels
Changlong Wu, Yifan Wang, Ananth Grama, Wojciech Szpankowski
International Conference on Machine Learning (ICML), 2023
Personal Projects
BiteEmo App Development
For a long time, I’ve observed something quite common around me: most people aren’t struggling with their weight because they don’t know what to eat or how to exercise. Instead, it’s often emotional issues—stress from work, social pressures, or just feeling down—that trigger unhealthy eating behaviors. Managing these emotions, rather than merely counting calories or forcing workouts into an already busy schedule, can be the key to better health. From my own experience, writing down my thoughts and feelings—doing what I call a “brain dump”—has always been incredibly therapeutic.