Niao He

When Scores Learn Geometry: Rate Separations under the Manifold Hypothesis

On the Benefits of Weight Normalization for Overparameterized Matrix Sensing

Landing with the Score: Riemannian Optimization through Denoising

A Schrödinger Eigenfunction Method for Long-Horizon Stochastic Optimal Control

PoLAR: Polar-Decomposed Low-Rank Adapter Representation

Scalable Neural Incentive Design with Parameterized Mean-Field Approximation

Natural Gradient VI: Guarantees for Non-Conjugate Models

AmorLIP: Efficient Language-Image Pretraining via Amortization

Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning

Zeroth-Order Optimization Finds Flat Minima

On the Crucial Role of Initialization for Matrix Factorization

Learning to Steer Markovian Agents under Model Uncertainty

Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective

Provable Maximum Entropy Manifold Exploration via Diffusion Models