ArXiv TLDR

José Miguel Hernández-Lobato

2 papers · Latest:

Statistical Machine Learning

Decoupled PFNs: Identifiable Epistemic-Aleatoric Decomposition via Structured Synthetic Priors

Decoupled PFNs use structured synthetic priors to identifiably separate epistemic and aleatoric uncertainty, improving sequential decision-making in noisy settings.

2605.06413
Statistical Machine Learning

Conditional Diffusion Sampling

Conditional Diffusion Sampling (CDS) combines Parallel Tempering with exact diffusion SDEs for efficient sampling from complex multimodal distributions.

2605.04013

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.