Cover Image

Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Van Assel, Hugues, De Brouwer, Edward, Saremi, Saeed, Scalia, Gabriele, Regev, Aviv
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning
by: Van Assel, Hugues, et al.
Published: (2025)

Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum
by: Lu, Wenquan, et al.
Published: (2025)

SubFlow: Sub-mode Conditioned Flow Matching for Diverse One-Step Generation
by: Lin, Yexiong, et al.
Published: (2026)

FREPix: Frequency-Heterogeneous Flow Matching for Pixel-Space Image Generation
by: Lin, Mingfeng, et al.
Published: (2026)

On The Role of K-Space Acquisition in MRI Reconstruction Domain-Generalization
by: Wattad, Mohammed, et al.
Published: (2025)

Optimizing Few-Step Generation with Adaptive Matching Distillation
by: Bai, Lichen, et al.
Published: (2026)

Click2Mask: Local Editing with Dynamic Mask Generation
by: Regev, Omer, et al.
Published: (2024)

Drifting Preference Optimization for One-Step Generative Models
by: Jiang, Zhou, et al.
Published: (2026)

Consistency Trajectory Matching for One-Step Generative Super-Resolution
by: You, Weiyi, et al.
Published: (2025)

SemanticGen: Video Generation in Semantic Space
by: Bai, Jianhong, et al.
Published: (2025)

Setting-Matched and Semantics-Scaled Benchmarking of One-Step Generative Models Against Multistep Diffusion and Flow Models
by: Ravishankar, Advaith, et al.
Published: (2026)

Exploring Diffusion and Flow Matching Under Generator Matching
by: Patel, Zeeshan, et al.
Published: (2024)

Training-Free Voice Conversion with Factorized Optimal Transport
by: Lobashev, Alexander, et al.
Published: (2025)

Feature-Space Generative Models for One-Shot Class-Incremental Learning
by: Foster, Jack, et al.
Published: (2026)

One Step Learning, One Step Review
by: Huang, Xiaolong, et al.
Published: (2024)

SoFlow: Solution Flow Models for One-Step Generative Modeling
by: Luo, Tianze, et al.
Published: (2025)

Hessian Geometry of Latent Space in Generative Models
by: Lobashev, Alexander, et al.
Published: (2025)

Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation
by: Chang, Yingshan, et al.
Published: (2024)

Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models
by: Nilaksh, et al.
Published: (2026)

Variational Flow Maps: Make Some Noise for One-Step Conditional Generation
by: Mammadov, Abbas, et al.
Published: (2026)

Semantic One-Dimensional Tokenizer for Image Reconstruction and Generation
by: Qu, Yunpeng, et al.
Published: (2026)

Adapt then Unlearn: Exploring Parameter Space Semantics for Unlearning in Generative Adversarial Networks
by: Tiwary, Piyush, et al.
Published: (2023)

Shape Generation via Weight Space Learning
by: Plattner, Maximilian, et al.
Published: (2025)

High-Order Matching for One-Step Shortcut Diffusion Models
by: Chen, Bo, et al.
Published: (2025)

One-Step Diffusion Distillation through Score Implicit Matching
by: Luo, Weijian, et al.
Published: (2024)

Multi-Scale Deep Learning for Colon Histopathology: A Hybrid Graph-Transformer Approach
by: Saremi, Sadra, et al.
Published: (2025)

Deep Linear Probe Generators for Weight Space Learning
by: Kahana, Jonathan, et al.
Published: (2024)

MARCO: Navigating the Unseen Space of Semantic Correspondence
by: Cuttano, Claudia, et al.
Published: (2026)

Trajectory Consistency for One-Step Generation on Euler Mean Flows
by: Li, Zhiqi, et al.
Published: (2026)

Diffusion Adversarial Post-Training for One-Step Video Generation
by: Lin, Shanchuan, et al.
Published: (2025)

Stepping Out of Similar Semantic Space for Open-Vocabulary Segmentation
by: Liu, Yong, et al.
Published: (2025)

Noise Consistency Training: A Native Approach for One-Step Generator in Learning Additional Controls
by: Luo, Yihong, et al.
Published: (2025)

InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
by: Liu, Xingchao, et al.
Published: (2023)

Semantic-aware Random Convolution and Source Matching for Domain Generalization in Medical Image Segmentation
by: Thaler, Franz, et al.
Published: (2025)

Training-Free Generation of Diverse and High-Fidelity Images via Prompt Semantic Space Optimization
by: Meng, Debin, et al.
Published: (2025)

Pushing the Boundaries of State Space Models for Image and Video Generation
by: Hong, Yicong, et al.
Published: (2025)

LASERS: LAtent Space Encoding for Representations with Sparsity for Generative Modeling
by: Li, Xin, et al.
Published: (2024)

Generalization of Diffusion Models Arises with a Balanced Representation Space
by: Zhang, Zekai, et al.
Published: (2025)

Embedding Space Selection for Detecting Memorization and Fingerprinting in Generative Models
by: He, Jack, et al.
Published: (2024)

Generative Modeling with Orbit-Space Particle Flow Matching
by: Wang, Sinan, et al.
Published: (2026)