Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees

Documenti analoghi

• Towards a mathematical theory for consistency training in diffusion models
  di: Li, Gen, et al.
  Pubblicazione: (2024)
• Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models
  di: Li, Gen, et al.
  Pubblicazione: (2023)
• Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model
  di: Li, Gen, et al.
  Pubblicazione: (2020)
• Settling the Sample Complexity of Model-Based Offline Reinforcement Learning
  di: Li, Gen, et al.
  Pubblicazione: (2022)
• Breaking AR's Sampling Bottleneck: Provable Acceleration via Diffusion Language Models
  di: Li, Gen, et al.
  Pubblicazione: (2025)