paper-with-me

Papers

Aligning Latent Geometry for Spherical Flow Matching in Image Generation

2026-05-14 · Tuna Han Salih Meral, Kaan Oktay, Hidir Yesiltepe, Adil Kaan Akan, Pinar Yanardag arxiv

Latent flow matching for image generation usually transports Gaussian noise to variational autoencoder latents along linear paths. Both endpoints, however, concentrate in thin spherical shells, and a Euclidean chord leaves those shells even when preprocessing aligns their radii. By decomposing each latent token into radial and angular components, we show through component-swap probes that decoded perceptual and semantic content is carried predominantly by direction, with radius contributing much less. We therefore project data latents onto a fixed token radius, use the radial projection of Gaussian noise as the spherical prior, finetune the decoder with the encoder frozen, and replace linear interpolation with spherical linear interpolation. The resulting geodesic paths stay on the sphere at every timestep, and their velocity targets are purely angular by construction. Under matched training, the method consistently improves class-conditional ImageNet-256 FID across different image tokenizers, leaves the diffusion architecture unchanged, and requires no auxiliary encoder or representation-alignment objective.

📄 PDF Abstract BibTeX arXiv:2605.15193

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Geometry-Aware Image Flow Matching

2026-05-24 · Junho Lee, Kwanseok Kim, Joonseok Lee arxiv

Recent advances in generative models highlight the power of geometry-aware modeling in manifold-constrained settings. Yet, for natural images, the field remains confined to Euclidean assumptions, failing to exploit the p…

Image Generation

Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions

2026-01-29 · Lingkai Kong, Anagha Satish, Hezi Jiang, Akseli Kangaslahti 외 arxiv

Reinforcement learning (RL) with combinatorial action spaces remains challenging because feasible action sets are exponentially large and governed by complex feasibility constraints, making direct policy parameterization…

Reinforcement Learning

Gromov-Hausdorff Distances for Comparing Product Manifolds of Model Spaces

2023-09-09 · Haitz Saez de Ocariz Borde, Alvaro Arroyo, Ismael Morales, Ingmar Posner 외

Recent studies propose enhancing machine learning models by aligning the geometric characteristics of the latent space with the underlying data structure. Instead of relying solely on Euclidean space, researchers have su…

Neural Latent Geometry Search: Product Manifold Inference via Gromov-Hausdorff-Informed Bayesian Optimization

2023-09-09 · NeurIPS 2023 11

Recent research indicates that the performance of machine learning models can be improved by aligning the geometry of the latent space with the underlying data structure. Rather than relying solely on Euclidean space, re…

Bayesian OptimizationInductive Bias

Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces

2026-04-30 · Andrew Bond, Ilkin Umut Melanlioglu, Erkut Erdem, Aykut Erdem arxiv

Modern visual world modeling systems increasingly rely on high-capacity architectures and large-scale data to produce plausible motion, yet they often fail to preserve underlying 3D geometry or physically consistent came…

Depth Estimation