MCLR: Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives

Documenti analoghi

• Towards Understanding the Mechanisms of Classifier-Free Guidance
  di: Li, Xiang, et al.
  Pubblicazione: (2025)
• FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation
  di: Chen, Siyi, et al.
  Pubblicazione: (2025)
• ForcingDAS: Unified and Robust Data Assimilation via Diffusion Forcing
  di: Jia, Yixuan, et al.
  Pubblicazione: (2026)
• Your Classifier Can Be Secretly a Likelihood-Based OOD Detector
  di: Burapacheep, Jirayu, et al.
  Pubblicazione: (2024)
• Learning Likelihood Ratios with Neural Network Classifiers
  di: Rizvi, Shahzar, et al.
  Pubblicazione: (2023)