---
format: "aidr-story-markdown/v1"
id: "5cea2a29d1090b9163abea20c3ca4e05cb28a5ed7564d0fc2b08afb4efbd952f"
canonical_url: "https://aidr.today/5cea2a29?lang=en"
title: "Thompson Sampling using Prior-fitted Diffusion Transformers"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-13T05:00:00.000Z"
category: "Research"
topics: ["inference"]
source_urls: ["https://arxiv.org/abs/2611.14656"]
summary: "Prior-fitted diffusion transformers perform Thompson sampling in-context at inference time after pre-training. The work develops practical non-Gaussian priors for general black-box functions, including unimodal functions."
---

# Thompson Sampling using Prior\-fitted Diffusion Transformers

> [Open the canonical story](<https://aidr.today/5cea2a29?lang=en>)

**Published:** 2026-11-13T05:00:00.000Z
**Category:** Research
**Topics:** inference

## Summary

Prior\-fitted diffusion transformers perform Thompson sampling in\-context at inference time after pre\-training\. The work develops practical non\-Gaussian priors for general black\-box functions, including unimodal functions\.

## Sources

- [Story source](<https://arxiv.org/abs/2611.14656>)