Publications

Representative Papers

• Computational and Statistical Guarantees of the \textit{c}-Rectified flow
  

  • Leda Wang, Zhehao Xu, Qiang Liu, Harrison H. Zhou

• Dynamical mean-field limit and replica-symmetric free energy for the orthogonally-invariant SK model
  

  • Zhou Fan, Theodor Misiakiewicz, Leda Wang, Garrett G. Wen

• Neural Networks Provably Learn Spectral Representations for Group Composition
  

  • Jianliang He, Leda Wang, Fengzhuo Zhang, Siyu Chen, Zhuoran Yang

• On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking
  

  • Jianliang He, Leda Wang, Siyu Chen, Zhuoran Yang

• High-dimensional learning dynamics of multi-pass Stochastic Gradient Descent in multi-index models
  

  • Zhou Fan, Leda Wang

• Inference in Randomized Least Squares and PCA via Normality of Quadratic Forms
  

  • Leda Wang, Zhixiang Zhang, Edgar Dobriban

• Understanding and Enhancing Mask-Based Pretraining towards Universal Representations
  

  • Mingze Dong, Leda Wang, Yuval Kluger

  • The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025

• The monotonicity of the Franz-Parisi potential is equivalent with Low-degree MMSE lower bounds
  

  • Kostantinos Tsirkas, Leda Wang, Ilias Zadik

  • Conference on Learning Theory (COLT), 2026

All Publications

• How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks
  

  • Ali Ansari et al.