4 papers
On the Edge of Memorization in Diffusion Models
Sam Buchanan, Druv Pai, Yi Ma +1
When do diffusion models reproduce their training data, and when are they able to generate samples beyond it? A practically relevant theoretical understanding of this interplay bet…
MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
Junzhe Li, Yutao Cui, Tao Huang +8
Although GRPO substantially enhances flow matching models in human preference alignment of image generation, methods such as FlowGRPO and DanceGRPO still exhibit inefficiency due t…
Beyond Self-Repellent Kernels: History-Driven Target Towards Efficient Nonlinear MCMC on General Graphs
Jie Hu, Yi-Ting Ma, Do Young Eun
We propose a history-driven target (HDT) framework in Markov Chain Monte Carlo (MCMC) to improve any random walk algorithm on discrete state spaces, such as general undirected grap…
Does Worst-Performing Agent Lead the Pack? Analyzing Agent Dynamics in Unified Distributed SGD
Jie Hu, Yi-Ting Ma, Do Young Eun
Distributed learning is essential to train machine learning algorithms across heterogeneous agents while maintaining data privacy. We conduct an asymptotic analysis of Unified Dist…