Skip to content

Conditioning Degenerate Diffusion Models

Sep 2026 · 0 citations · 35 references
Computer Science

TL;DR

This work uses causal optimal transport to define loss functions that identify a minimum-entropy control for guidance under minimal assumptions in conditioned generative models.

Abstract

Current conditioned generative models heavily rely on score functions for guidance during training. When the generative model is a diffusion process with a singular diffusion coefficient and the underlying (conditional) densities either do not exist or are not smooth, we use causal optimal transport to define \emph{approximate} loss functions that identify a minimum-entropy control for guidance under minimal assumptions. Our approach relies on causal optimal transport and its characterization through the predictable representation property of (conditioned) diffusion processes whose associated martingale problem is well posed, \`a la \"Ust\"unel.

View source

Similar papers

Preprint Sep 2026

Generative bootstrap processes

We study generative bootstrap processes obtained by resampling from fitted generative distributions. We establish necessary and sufficient conditions for their conditional weak convergence to the $P$-Brownian bridge, formulated in terms of finite-dimensional conditional weak convergence and conditional asymptotic equic...

Zi-Ming Lin, Fang Han · 0 citations

Optimal Transport Dropout for Structured Predictive Uncertainty

Optimal Transport Dropout (OTD) is introduced, which offers a way to learn structured predictive uncertainty without explicit posterior inference or ensembles of independently trained predictors.

Giacomo Lorenzon, Francesco Regazzoni · 0 citations
Preprint Aug 2026

A Plug-in Interpretation of Conditioning in Score-Based Diffusion Models

A conditioning mechanism for diffusion models based on multi-speed joint diffusion of the target and the condition learns an unconditional joint score network and enforces conditioning at inference via a plug-in correction term, and derives explicit conditional reverse-time SDEs and approximate probability-flow ODEs.

Libo Chen, Souvik Ghosh, Teo Deveney et al. · 0 citations

Simplex Diffusion Models

Simplex Diffusion Models (SDMs) are proposed, a framework that lifts the diffusion process to the probability simplex to represent beliefs over categories and can carry uncertainty across denoising steps, which mitigates information collapse.

Justin Deschenaux, Alexandre Galashov, Andrew Campbell et al. · 2 citations
#machine learning Preprint Aug 2026

Simulation-free and finite-time diffusion model

A framework for designing the reference process that achieves tractable time-dependent conditional distributions and then construct the reference process realizing them as its marginals is proposed, revealing that score matching is not fundamental to diffusion-model training but instead emerges naturally through revers...

Kentaro Kaba, Masayuki Ohzeki, Yuki Sughiyama · 0 citations
#natural language process... Preprint Aug 2026

Simplex Relaxation for Discrete Diffusion

Simplax is introduced, an exact Dirichlet--categorical augmentation that couples each corrupted categorical state with an auxiliary simplex-valued variable while preserving the original uniform diffusion process as its categorical marginal.

Jinya Sakurai, Patrick Pynadath, Satoshi Hayakawa et al. · 1 citation

Related blog posts

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

MIT News · Artificial Intelligence Oct 23, 2026

Q&A: How AI came to model the “messy” human mind

Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.