Molei Tao

6 papers Georgia Tech

• A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective
• Fast Non-Log-Concave Sampling under Nonconvex Equality and Inequality Constraints with Landing
• Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithms
• MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control
• Non-equilibrium Annealed Adjoint Sampler
• Variational Learning Finds Flatter Solutions at the Edge of Stability