3 papers
cs.LG2026
Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions
Le-Tuyet-Nhi Pham, Giovanni Conforti, Zhenjie Ren +1
Flow Matching has recently emerged as a popular class of generative models for simulating a target distribution from samples drawn from a source distribution . This fram…
cs.LG2025
Non-Asymptotic Convergence of Discrete Diffusion Models: Masked and Random Walk dynamics
Giovanni Conforti, Alain Durmus, Le-Tuyet-Nhi Pham +1
Diffusion models for continuous state spaces based on Gaussian noising processes are now relatively well understood from both practical and theoretical perspectives. In contrast, r…
stat.ML2025
Bit-Level Discrete Diffusion with Markov Probabilistic Models: An Improved Framework with Sharp Convergence Bounds under Minimal Assumptions
Le-Tuyet-Nhi Pham, Dario Shariatian, Antonio Ocello +2
This paper introduces Discrete Markov Probabilistic Models (DMPMs), a novel discrete diffusion algorithm for discrete data generation. The algorithm operates in discrete bit space,…