---
type: "post"
id: "mclr-fine-tunes-diffusion-models-to-maximize-inter-1d808b"
slug: "mclr-fine-tunes-diffusion-models-to-maximize-inter-1d808b"
title: "MCLR fine-tunes diffusion models to maximize inter-class likelihood ratios, internalizing classifier-free guidance effects ."
description: "MCLR is a research paper by Xiang Li, Yixuan Jia, Xiao Li, Jeffrey A."
retrieval_nugget: "MCLR is a research paper by Xiang Li, Yixuan Jia, Xiao Li, Jeffrey A."
published_at: "2026-10-24"
updated_at: "2026-10-24"
record_date: "2026-10-24"
date_kind: "published_at"
topics: ["models"]
entities: ["MCLR","Classifier-Free Guidance"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "MCLR introduces an objective to maximize inter-class likelihood ratios, improving guidance-free conditional generation and theoretically interpreting classifier-free guidance as implicit contrastive alignment."
prior_refs: ["memory:329b4e82-f825-8b1e-a0e9-91fbf85de324"]
source_url: "https://arxiv.org/abs/2603.22364"
source_urls: ["https://arxiv.org/abs/2603.22364"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:mclr-fine-tunes-diffusion-models-to-maximize-inter-1d808b"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/mclr-fine-tunes-diffusion-models-to-maximize-inter-1d808b/","markdown":"https://newruntime.com/posts/mclr-fine-tunes-diffusion-models-to-maximize-inter-1d808b.md","json":"https://newruntime.com/posts/mclr-fine-tunes-diffusion-models-to-maximize-inter-1d808b.json"}
---

# MCLR fine-tunes diffusion models to maximize inter-class likelihood ratios, internalizing classifier-free guidance effects .

## Retrieval answer

MCLR is a research paper by Xiang Li, Yixuan Jia, Xiao Li, Jeffrey A.

MCLR is a research paper by Xiang Li, Yixuan Jia, Xiao Li, Jeffrey A. Fessler, Rongrong Wang, and Qing Qu on conditional diffusion models. Its fourth arXiv version was posted on October 20, 2026; the first version was submitted on March 23, 2026.

The authors propose fine-tuning models with an inter-class likelihood-ratio maximization objective, called MCLR. The stated aim is to strengthen class-specific structure in samples generated from the same noise under different labels, reducing reliance on classifier-free guidance (CFG) during sampling.

The paper reports improved guidance-free conditional generation across multiple models and datasets, and says MCLR narrows the gap with CFG. It also proves, under its sample-adaptively weighted ELBO approximation, that the CFG-guided score is the unique minimizer of its objective. The arXiv record does not establish a production implementation, public code, benchmark figures in the abstract, or deployment results.

Source: https://arxiv.org/abs/2603.22364

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Models](https://newruntime.com/topics/models.md): Explore the models topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)