paper-with-me

Papers

Interleaved Gibbs Diffusion for Constrained Generation

2025-02-19 · Gautham Govind Anil, Sachin Yadav, Dheeraj Nagaraj, Karthikeyan Shanmugam, Prateek Jain

We introduce Interleaved Gibbs Diffusion (IGD), a novel generative modeling framework for mixed continuous-discrete data, focusing on constrained generation problems. Prior works on discrete and continuous-discrete diffusion models assume factorized denoising distribution for fast generation, which can hinder the modeling of strong dependencies between random variables encountered in constrained generation. IGD moves beyond this by interleaving continuous and discrete denoising algorithms via a discrete time Gibbs sampling type Markov chain. IGD provides flexibility in the choice of denoisers, allows conditional generation via state-space doubling and inference time scaling via the ReDeNoise method. Empirical evaluations on three challenging tasks-solving 3-SAT, generating molecule structures, and generating layouts-demonstrate state-of-the-art performance. Notably, IGD achieves a 7% improvement on 3-SAT out of the box and achieves state-of-the-art results in molecule generation without relying on equivariant diffusion or domain-specific architectures. We explore a wide range of modeling, and interleaving strategies along with hyperparameters in each of these problems.

📄 PDF Abstract BibTeX arXiv:2502.13450

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Constrained Diffusion Models with Primal-Dual Inference

2026-06-15 · Samar Hadou, Yigit Berkay Uslu, Alejandro Ribeiro arxiv

This paper develops constrained diffusion models with primal-dual inference (PDI) to sample from optimal distributions of entropy-regularized optimization problems with \emph{average} constraints. We formalize constraine…

Loom: Diffusion-Transformer for Interleaved Generation

2025-12-20 · Mingcheng Ye, Jiaming Liu, Yiren Song arxiv

Interleaved text-image generation aims to jointly produce coherent visual frames and aligned textual descriptions within a single sequence, enabling tasks such as style transfer, compositional synthesis, and procedural t…

Image GenerationStyle Transfer

SIGMA: Selective-Interleaved Generation with Multi-Attribute Tokens

2026-02-07 · Xiaoyan Zhang, Zechen Bai, Haofan Wang, Yiren Song arxiv

Recent unified models such as Bagel demonstrate that paired image-edit data can effectively align multiple visual tasks within a single diffusion transformer. However, these models remain limited to single-condition inpu…

SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement

2025-06-09 · Chenyu Yang, Shuai Wang, Hangting Chen, Wei Tan 외

Generating music with coherent structure, harmonious instrumental and vocal elements remains a significant challenge in song generation. Existing language models and diffusion-based methods often struggle to balance glob…

Music Generation

Split Gibbs Discrete Diffusion Posterior Sampling

2025-03-03 · Wenda Chu, Yang song, Yisong Yue

We study the problem of posterior sampling in discrete-state spaces using discrete diffusion models. While posterior sampling methods for continuous diffusion models have achieved remarkable progress, analogous methods f…