From Global to Factor-Wise Expert Composition in Discrete Diffusion Models

• URL: http://arxiv.org/abs/2607.11758v1
• Date: Mon, 13 Jul 2026 16:22:01 GMT
• Title: From Global to Factor-Wise Expert Composition in Discrete Diffusion Models
• Abstract summary: We propose FactorDiff - a factor-wise composition framework for diffusion models.<n>We instantiate this framework with spatial/pixel-level compositions and validate it on the ARC-AGI benchmark.
• Score: 5.756282731737539
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Discrete diffusion models offer a powerful framework for solving complex reasoning tasks, particularly through compositional generation, which combines multiple pre-trained experts to generalize beyond their individual training data. Recent theoretical corrections introduce time-dependent mixing weights to better align composed diffusion dynamics with the intended target. However, these methods are fundamentally limited by working on a per-sample basis, treating each generated state monolithically and ignoring the potential spatial or functional specializations of different experts. In this work, we address this limitation by proposing FactorDiff - a factor-wise composition framework for diffusion models. We posit that samples can be further decomposed into smaller factors, and propose a sampling process that dynamically routes each factor to the most relevant expert. We instantiate this framework with spatial/pixel-level compositions and validate it on the ARC-AGI benchmark, demonstrating that simple factor-specific routing consistently outperforms complex global scalar weighting schemes on tasks that require logical consistency and spatial disentanglement.

Related papers

• CDFM: Towards a General-Purpose Causal Discovery Foundation Model [62.32138962508216]
  Causal discovery is the process of recovering underlying causal structures from observational data.<n>We formulate the Causal Discovery Foundation Model (CDFM) as a unified, general-purpose framework for zero-shot structural inference.<n>CDFM consistently outperforms traditional algorithms, driving a paradigm shift toward a general-purpose causal discovery foundation model.
  arXiv  Detail & Related papers  (2026-07-13T12:58:28Z)
• Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning [83.65494573724904]
  We develop a principled MOL framework for diffusion models with limited data.<n>We propose a two-stage training procedure that first fits lightweight specialist models from limited paired data.<n>We establish bounds generalization showing that the required number of paired samples only depends on the complexity of the specialist model classes.
  arXiv  Detail & Related papers  (2026-05-24T18:19:40Z)
• Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution [76.66229730098759]
  In real-world image super-resolution (Real-ISR), existing approaches mainly rely on fine-tuning pre-trained diffusion models.<n>We propose a Mixture-of-Ranks (MoR) architecture for single-step image super-resolution.<n>We introduce a fine-grained expert partitioning strategy that treats each rank in LoRA as an independent expert.
  arXiv  Detail & Related papers  (2025-11-20T04:11:44Z)
• Symphony-MoE: Harmonizing Disparate Pre-trained Models into a Coherent Mixture-of-Experts [18.18231276284727]
  Mixture-of-Experts (MoE) models enable scalable performance by activating large parameter sets sparsely.<n>Recent work employs upcycling, reusing a single pre-trained dense model by replicating its feed-forward network (FFN) layers into experts.<n>This paper addresses this limitation by constructing powerful MoE models using experts sourced from multiple identically-architected but disparate pre-trained models.
  arXiv  Detail & Related papers  (2025-09-23T02:07:14Z)
• Sparse Mixture-of-Experts for Compositional Generalization: Empirical Evidence and Theoretical Foundations of Optimal Sparsity [89.81738321188391]
  This study investigates the relationship between task complexity and optimal sparsity in SMoE models.<n>We show that the optimal sparsity lies between minimal activation (1-2 experts) and full activation, with the exact number scaling proportionally to task complexity.
  arXiv  Detail & Related papers  (2024-10-17T18:40:48Z)
• Mixture of Efficient Diffusion Experts Through Automatic Interval and Sub-Network Selection [63.96018203905272]
  We propose to reduce the sampling cost by pruning a pretrained diffusion model into a mixture of efficient experts. We demonstrate the effectiveness of our method, DiffPruning, across several datasets.
  arXiv  Detail & Related papers  (2024-09-23T21:27:26Z)
• Generalization Error Analysis for Sparse Mixture-of-Experts: A Preliminary Study [65.11303133775857]
  Mixture-of-Experts (MoE) computation amalgamates predictions from several specialized sub-models (referred to as experts) Sparse MoE selectively engages only a limited number, or even just one expert, significantly reducing overhead while empirically preserving, and sometimes even enhancing, performance.
  arXiv  Detail & Related papers  (2024-03-26T05:48:02Z)
• Physics-Informed Diffusion Models [0.0]
  We present a framework that unifies generative modeling and partial differential equation fulfillment.<n>Our approach reduces the residual error by up to two orders of magnitude compared to previous work in a fluid flow case study.
  arXiv  Detail & Related papers  (2024-03-21T13:52:55Z)
• Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reduction [22.567754688492414]
  Cross-device Federated Learning (FL) faces significant challenges where low-end clients that could potentially make unique contributions are excluded from training large models due to their resource bottlenecks. Recent research efforts have focused on model-heterogeneous FL, by extracting reduced-size models from the global model and applying them to local clients accordingly. This paper presents a unifying framework for heterogeneous FL algorithms with online model extraction and provides a general convergence analysis for the first time.
  arXiv  Detail & Related papers  (2023-10-12T19:07:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.