PPL
Guannan Qu
Papers (4)
Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style SmoothingEmergent and Subliminal Misalignment Through the Lens of Data-Mediated TransferRevisiting Policy Gradients for Restricted Policy Classes: Escaping Myopic Local Optima with $k$-step Policy GradientsTowards Effective Theory of LLMs: A Representation Learning Approach