Related papers: Spatial Reasoners for Continuous Variables in Any Domain

Spatial Reasoners for Continuous Variables in Any Domain

URL: http://arxiv.org/abs/2507.10768v1
Date: Mon, 14 Jul 2025 19:46:54 GMT
Title: Spatial Reasoners for Continuous Variables in Any Domain
Authors: Bart Pogodzinski, Christopher Wewer, Bernt Schiele, Jan Eric Lenssen,
Abstract summary: We present a framework to perform spatial reasoning over continuous variables with generative denoising models.<n>We provide interfaces to control variable mapping from arbitrary data domains, generative model paradigms, and inference strategies.
Score: 49.83744014336816
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: We present Spatial Reasoners, a software framework to perform spatial reasoning over continuous variables with generative denoising models. Denoising generative models have become the de-facto standard for image generation, due to their effectiveness in sampling from complex, high-dimensional distributions. Recently, they have started being explored in the context of reasoning over multiple continuous variables. Providing infrastructure for generative reasoning with such models requires a high effort, due to a wide range of different denoising formulations, samplers, and inference strategies. Our presented framework aims to facilitate research in this area, providing easy-to-use interfaces to control variable mapping from arbitrary data domains, generative model paradigms, and inference strategies. Spatial Reasoners are openly available at https://spatialreasoners.github.io/

Related papers

Be Decisive: Noise-Induced Layouts for Multi-Subject Generation [56.80513553424086]
Complex prompts lead to subject leakage, causing inaccuracies in quantities, attributes, and visual features.<n>We introduce a new approach that predicts a spatial layout aligned with the prompt, derived from the initial noise, and refines it throughout the denoising process.<n>Our method employs a small neural network to predict and refine the evolving noise-induced layout at each denoising step.
arXiv Detail & Related papers (2025-05-27T17:54:24Z)
Consistent World Models via Foresight Diffusion [56.45012929930605]
We argue that a key bottleneck in learning consistent diffusion-based world models lies in the suboptimal predictive ability.<n>We propose Foresight Diffusion (ForeDiff), a diffusion-based world modeling framework that enhances consistency by decoupling condition understanding from target denoising.
arXiv Detail & Related papers (2025-05-22T10:01:59Z)
Simple and Critical Iterative Denoising: A Recasting of Discrete Diffusion in Graph Generation [0.0]
dependencies between intermediate noisy states lead to error accumulation and propagation during the reverse denoising process.<n>We propose a novel framework called Simple Iterative Denoising, which simplifies discrete diffusion and circumvents the issue.<n>Our empirical evaluations demonstrate that the proposed method significantly outperforms existing discrete diffusion baselines in graph generation tasks.
arXiv Detail & Related papers (2025-03-27T15:08:58Z)
Spatial Reasoning with Denoising Models [49.83744014336816]
We introduce a framework to perform reasoning over sets of continuous variables via denoising generative models.<n>For the first time, that order of generation can successfully be predicted by the denoising network itself.<n>Using these findings, we can increase the accuracy of specific reasoning tasks from 1% to >50%.
arXiv Detail & Related papers (2025-02-28T14:08:30Z)
Generalized Diffusion Model with Adjusted Offset Noise [1.7767466724342067]
We propose a generalized diffusion model that naturally incorporates additional noise within a rigorous probabilistic framework.<n>We derive a loss function based on the evidence lower bound, establishing its theoretical equivalence to offset noise with certain adjustments.<n>Experiments on synthetic datasets demonstrate that our model effectively addresses brightness-related challenges and outperforms conventional methods in high-dimensional scenarios.
arXiv Detail & Related papers (2024-12-04T08:57:03Z)
Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction [88.65168366064061]
We introduce Discrete Denoising Posterior Prediction (DDPP), a novel framework that casts the task of steering pre-trained MDMs as a problem of probabilistic inference. Our framework leads to a family of three novel objectives that are all simulation-free, and thus scalable. We substantiate our designs via wet-lab validation, where we observe transient expression of reward-optimized protein sequences.
arXiv Detail & Related papers (2024-10-10T17:18:30Z)
GUD: Generation with Unified Diffusion [40.64742332352373]
Diffusion generative models transform noise into data by inverting a process that progressively adds noise to data samples. We develop a unified framework for diffusion generative models with greatly enhanced design freedom.
arXiv Detail & Related papers (2024-10-03T16:51:14Z)
Conditional Generative Modeling via Learning the Latent Space [54.620761775441046]
We propose a novel framework for conditional generation in multimodal spaces. It uses latent variables to model generalizable learning patterns. At inference, the latent variables are optimized to find optimal solutions corresponding to multiple output modes.
arXiv Detail & Related papers (2020-10-07T03:11:34Z)
Factorized Deep Generative Models for Trajectory Generation with Spatiotemporal-Validity Constraints [10.960924101404498]
Deep generative models for trajectory data can learn expressively explanatory models for sophisticated latent patterns. We first propose novel deep generative models factorizing time-variant and time-invariant latent variables. We then develop new inference strategies based on variational inference and constrained optimization to thetemporal validity.
arXiv Detail & Related papers (2020-09-20T02:06:36Z)

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