Equivariant Latent Alignment via Flow Matching under Group Symmetries

• URL: http://arxiv.org/abs/2605.30705v2
• Date: Tue, 02 Jun 2026 23:56:56 GMT
• Title: Equivariant Latent Alignment via Flow Matching under Group Symmetries
• Abstract summary: equivariant representation learning has emerged as a powerful framework for constructing latent spaces where analytically known group transformations could act directly.<n>Existing approaches often suffer from latent misalignment, a discrepancy between the intended group action and the actually required transformations in the latent space.<n>We propose Residual Latent Flow, a flow-based framework that corrects the misaligned latents.
• Score: 18.655367238679496
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Geometry-aware generative models and novel view synthesis approaches have shown strong potential in visual fidelity and consistency. In parallel, equivariant representation learning has emerged as a powerful framework for constructing latent spaces where analytically known group transformations could act directly, capturing geometric structure in data and enhancing both interpretability and generalization in novel view synthesis. However, we identify that existing approaches often suffer from latent misalignment, a discrepancy between the intended group action and the actually required transformations in the latent space. Consequently, the learned latents often fail to consistently preserve the equivariant relations imposed by the underlying group symmetry. To address this, we propose Residual Latent Flow, a flow-based framework that corrects the misaligned latents, thereby improving compliance with the underlying equivariance relation. Our comprehensive experiments show that our method significantly reduces latent misalignment and improves novel view synthesis quality, under rotation groups SO(n).

Related papers

• Groupoid-Based Internal State Representations for Reinforcement Learning with Local Symmetries [1.1470070927586018]
  We propose a reinforcement learning framework using groupoids to capture local, state-dependent symmetries and support the dy- namic discovery of equivalence structures.<n> Empirical results demonstrate that the proposed groupoid-based approach improves sample efficiency and convergence in dense and large-scale environments exhibiting strong partial symmetries.
  arXiv  Detail & Related papers  (2026-09-11T16:32:58Z)
• Commutator-Induced Uncertainty in VAEs [20.84327211490012]
  Variational autoencoders (VAEs) often struggle to represent non-commutative structure in learned latent spaces.<n>We introduce a Lie Group VAE framework that combines geometric and algebraic perspectives on uncertainty.<n>We evaluate the framework on dSprites, 3DShapes, 3DCars, and CelebA against generic and symmetry-aware baselines.
  arXiv  Detail & Related papers  (2026-05-22T10:03:46Z)
• Probability-Conserving Flow Guidance [49.03107678763765]
  Adaptive Manifold Guidance (AdaMaG) improves realism, reduces hallucinations, and controlled desaturation in high-guidance.<n>Across image generation benchmarks, AdaMaG improves realism, reduces hallucinations, and controlled desaturation in high-guidance.
  arXiv  Detail & Related papers  (2026-05-19T16:34:01Z)
• Anisotropic Modality Align [91.23979617826926]
  Training multimodal large language models has long been limited by the scarcity of high-quality paired multimodal data.<n>Recent studies show that the shared representation space of pretrained multimodal contrastive models can serve as a bridge, enabling models to perform multimodal training with unimodal data.<n>The core obstacle lies in the persistent Modality Gap in the shared space.
  arXiv  Detail & Related papers  (2026-05-08T14:53:24Z)
• GeodesicNVS: Probability Density Geodesic Flow Matching for Novel View Synthesis [54.39598154430305]
  We propose a Data-to-Data Flow Matching framework that learns deterministic transformations directly between paired views.<n>PDG-FM constrains flow trajectories using geodesic interpolants derived from probability density metrics of pretrained diffusion models.<n>These results highlight the advantages of incorporating data-dependent geometric regularization into deterministic flow matching for consistent novel view generation.
  arXiv  Detail & Related papers  (2026-03-01T09:30:11Z)
• Invariance on Manifolds: Understanding Robust Visual Representations for Place Recognition [19.200074425090595]
  We propose a Second-Order Geometric Statistics framework that inherently captures geometric stability without training.<n>Our approach introduces a training-free framework built upon fixed, pre-trained backbones, achieving strong zero-shot generalization without parameter updates.
  arXiv  Detail & Related papers  (2026-01-31T18:12:29Z)
• Relative Representations: Topological and Geometric Perspectives [50.85040046976025]
  Relative representations are an established approach to zero-shot model stitching.<n>We introduce a normalization procedure in the relative transformation, resulting in invariance to non-isotropic rescalings and permutations.<n>Second, we propose to deploy topological densification when fine-tuning relative representations, a topological regularization loss encouraging clustering within classes.
  arXiv  Detail & Related papers  (2024-09-17T08:09:22Z)
• Structure-preserving GANs [6.438897276587413]
  We introduce structure-preserving GANs as a data-efficient framework for learning distributions. We show that we can reduce the discriminator space to its projection on the invariant discriminator space. We contextualize our framework by building symmetry-preserving GANs for distributions with intrinsic group symmetry.
  arXiv  Detail & Related papers  (2022-02-02T16:40:04Z)
• Tensor Component Analysis for Interpreting the Latent Space of GANs [41.020230946351816]
  This paper addresses the problem of finding interpretable directions in the latent space of pre-trained Generative Adversarial Networks (GANs) Our scheme allows for both linear edits corresponding to the individual modes of the tensor, and non-linear ones that model the multiplicative interactions between them. We show experimentally that we can utilise the former to better separate style- from geometry-based transformations, and the latter to generate an extended set of possible transformations.
  arXiv  Detail & Related papers  (2021-11-23T09:14:39Z)
• Topographic VAEs learn Equivariant Capsules [84.33745072274942]
  We introduce the Topographic VAE: a novel method for efficiently training deep generative models with topographically organized latent variables. We show that such a model indeed learns to organize its activations according to salient characteristics such as digit class, width, and style on MNIST. We demonstrate approximate equivariance to complex transformations, expanding upon the capabilities of existing group equivariant neural networks.
  arXiv  Detail & Related papers  (2021-09-03T09:25:57Z)
• Inverse Learning of Symmetries [71.62109774068064]
  We learn the symmetry transformation with a model consisting of two latent subspaces. Our approach is based on the deep information bottleneck in combination with a continuous mutual information regulariser. Our model outperforms state-of-the-art methods on artificial and molecular datasets.
  arXiv  Detail & Related papers  (2020-02-07T13:48:52Z)

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.