Difan Zou

Computer Science · Physical Sciences

25h-index2.6kcitations150works0.72yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Stochastic Gradient Optimization Techniques(33), Optical Wireless Communication Technologies(19), Sparse and Compressive Sensing Techniques(15), Domain Adaptation and Few-Shot Learning(15), Neural Networks and Applications(13)

Publications148 total

Scaling Laws for Precision in High-Dimensional Linear Regression
arXiv (Cornell University)·2026Open Access
Scaling Laws for Precision in High-Dimensional Linear Regression
arXiv (Cornell University)·2026Open Access
The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradient
arXiv (Cornell University)·2026Open Access
The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradient
ArXiv.org·2026Open Access
DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders
arXiv (Cornell University)·2026Open Access
DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders
ArXiv.org·2026Open Access
ProFlow: Zero-Shot Physics-Consistent Sampling via Proximal Flow Guidance
arXiv (Cornell University)·2026Open Access
ProFlow: Zero-Shot Physics-Consistent Sampling via Proximal Flow Guidance
ArXiv.org·2026Open Access
Differentiable Evolutionary Reinforcement Learning
arXiv (Cornell University)·2025Open Access
Bidirectional Joint State–Memory Deep Bayesian Smoother for Motion Estimation
IEEE Transactions on Aerospace and Electronic Systems·2025
Learning under Quantization for High-Dimensional Linear Regression
ArXiv.org·2025Open Access
How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?
arXiv (Cornell University)·2025Open Access
Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning
arXiv (Cornell University)·2025Open Access
Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory
arXiv (Cornell University)·2025Open Access
Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation
arXiv (Cornell University)·2025Open Access
Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders
arXiv (Cornell University)·2025Open Access
F-Adapter: Frequency-Adaptive Parameter-Efficient Fine-Tuning in Scientific Machine Learning
arXiv (Cornell University)·2025Open Access
Towards Theoretical Understanding of Transformer Test-Time Computing: Investigation on In-Context Linear Regression
arXiv (Cornell University)·2025Open Access
Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMs
arXiv (Cornell University)·2025Open Access
Parallelized Autoregressive Visual Generation
2025· 2 cited
page 1 of 8Next →

Frequent Co-authors

Quanquan Gu(30), Zhengyuan Xu(15), Pan Xu(12), Chen Gong(11), Jinghui Chen(7), Johannes Bracher(6), Tilmann Gneiting(6), Weitong Zhang(6), Geoffrey Fairchild(6), Ajitesh Srivastava(5), Lingxiao Wang(5), Lauren Ancel Meyers(4), YangQuan Chen(4), Lihong Guo(4), Yuan Cao(4), Marcin Bodych(4), Lauren Castro(4), Isaac Michaud(4), Estee Y. Cramer(3), Evan L Ray(3)