Publications

* denotes equal contribution. See also Google Scholar.

Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control
Bolian Li, Yifan Wang, Yi Ding, Anamika Lochab, Ananth Grama, Ruqi Zhang

SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology
Yifan Wang, Bolian Li, David Cho, Ruqi Zhang, Fanping Sui, Ananth Grama

LLMs Can Get “Brain Rot”!
Shuo Xing*, Junyuan Hong*, Yifan Wang, Runjin Chen, Zhenyu Zhang, Ananth Grama, Zhengzhong Tu, Zhangyang Wang

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

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