A Statistical Theory of Contrastive Pre-training and Multimodal Generative AI

Documenti analoghi

• A Statistical Theory of Contrastive Learning via Approximate Sufficient Statistics
  di: Lin, Licong, et al.
  Pubblicazione: (2025)
• Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining
  di: Lin, Licong, et al.
  Pubblicazione: (2023)
• Improved Scaling Laws in Linear Regression via Data Reuse
  di: Lin, Licong, et al.
  Pubblicazione: (2025)
• An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization
  di: Chen, Minshuo, et al.
  Pubblicazione: (2024)
• Semi-parametric inference based on adaptively collected data
  di: Lin, Licong, et al.
  Pubblicazione: (2023)