SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.16797 · 2026

Adaptive Moments are Surprisingly Effective for Plug-and-Play Diffusion Sampling

Kilian Weinberger, Carla Gomes, Justin Lovelace, Christian Belardi

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Guided diffusion sampling relies on approximating often intractable likelihood scores, which introduces significant noise into the sampling dynamics. We propose using adaptive moment estimation to stabilize these noisy likelihood scores during sampling. Despite its simplicity, our approach achieves state-of-theart results on image restoration and class-conditional generation tasks, outperforming more complicated methods, which are often computationally more expensive. We provide empirical analysis of our method on both synthetic and real data, demonstrating that mitigating gradient noise through adaptive moments offers an effective way to improve alignment. Our code is available at https://github.com/christianbelardi/adam-guidance.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2603.16797")
get_code_for_paper("2603.16797")
have("2603.16797")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2603.16797.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2603.16797.svg)](https://syntology.ai/paper/2603.16797)

Connect an agent — have() is free.