Cover Image

Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Davtyan, Aram, Dadi, Leello Tadesse, Cevher, Volkan, Favaro, Paolo
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

Learn the Force We Can: Enabling Sparse Motion Control in Multi-Object Video Generation
by: Davtyan, Aram, et al.
Published: (2023)

Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks
by: Liu, Fanghui, et al.
Published: (2024)

Efficient Continual Finite-Sum Minimization
by: Mavrothalassitis, Ioannis, et al.
Published: (2024)

KOALA: A Kalman Optimization Algorithm with Loss Adaptivity
by: Davtyan, Aram, et al.
Published: (2021)

CAGE: Unsupervised Visual Composition and Animation for Controllable Video Generation
by: Davtyan, Aram, et al.
Published: (2024)

Communication-Inspired Tokenization for Structured Image Representations
by: Davtyan, Aram, et al.
Published: (2026)

The Last Mile to Supervised Performance: Semi-Supervised Domain Adaptation for Semantic Segmentation
by: Morales-Brotons, Daniel, et al.
Published: (2024)

Multilinear Operator Networks
by: Cheng, Yixin, et al.
Published: (2024)

KOALA++: Efficient Kalman-Based Optimization with Gradient-Covariance Products
by: Xia, Zixuan, et al.
Published: (2025)

From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models
by: Acuaviva, Pablo, et al.
Published: (2025)

Masked and Shuffled Blind Spot Denoising for Real-World Images
by: Chihaoui, Hamadi, et al.
Published: (2024)

PaddingFlow: Improving Normalizing Flows with Padding-Dimensional Noise
by: Meng, Qinglong, et al.
Published: (2024)

Membership Inference Attacks against Large Vision-Language Models
by: Li, Zhan, et al.
Published: (2024)

Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing
by: Kim, Jaihoon, et al.
Published: (2025)

Bidirectional Normalizing Flow: From Data to Noise and Back
by: Lu, Yiyang, et al.
Published: (2025)

Straighter Flow Matching via a Diffusion-Based Coupling Prior
by: Xing, Siyu, et al.
Published: (2023)

VCT: Training Consistency Models with Variational Noise Coupling
by: Silvestri, Gianluigi, et al.
Published: (2025)

Improved Mean Flows: On the Challenges of Fastforward Generative Models
by: Geng, Zhengyang, et al.
Published: (2025)

The Coupling Within: Flow Matching via Distilled Normalizing Flows
by: Berthelot, David, et al.
Published: (2026)

ODE$_t$(ODE$_l$): Shortcutting the Time and the Length in Diffusion and Flow Models for Faster Sampling
by: Gudovskiy, Denis, et al.
Published: (2025)

Improving Diffusion-Based Generative Models via Approximated Optimal Transport
by: Kim, Daegyu, et al.
Published: (2024)

Robustness in Both Domains: CLIP Needs a Robust Text Encoder
by: Rocamora, Elias Abad, et al.
Published: (2025)

The Curse of Conditions: Analyzing and Improving Optimal Transport for Conditional Flow-Based Generation
by: Cheng, Ho Kei, et al.
Published: (2025)

AlphaFlow: Understanding and Improving MeanFlow Models
by: Zhang, Huijie, et al.
Published: (2025)

FREE: Faster and Better Data-Free Meta-Learning
by: Wei, Yongxian, et al.
Published: (2024)

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

Composition of Memory Experts for Diffusion World Models
by: Stapf, Sebastian, et al.
Published: (2026)

Simple ReFlow: Improved Techniques for Fast Flow Models
by: Kim, Beomsu, et al.
Published: (2024)

Efficient and Effective Methods for Mixed Precision Neural Network Quantization for Faster, Energy-efficient Inference
by: Bablani, Deepika, et al.
Published: (2023)

Couple to Control: Joint Initial Noise Design in Diffusion Models
by: Jia, Jing, et al.
Published: (2026)

Progressive Data Dropout: An Embarrassingly Simple Approach to Faster Training
by: Sathiyanarayanan, Shriram M, et al.
Published: (2025)

Improving Consistency Models with Generator-Augmented Flows
by: Issenhuth, Thibaut, et al.
Published: (2024)

Provably Improving Generalization of Few-Shot Models with Synthetic Data
by: Nguyen, Lan-Cuong, et al.
Published: (2025)

Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction Tuning
by: Wu, Rujie, et al.
Published: (2026)

Noise2Noise Denoising of CRISM Hyperspectral Data
by: Platt, Robert, et al.
Published: (2024)

Improving Denoising Diffusion Models via Simultaneous Estimation of Image and Noise
by: Zhang, Zhenkai, et al.
Published: (2023)

Efficient Whole Slide Image Classification through Fisher Vector Representation
by: Gupta, Ravi Kant, et al.
Published: (2024)

Noise-Aware Generalization: Robustness to In-Domain Noise and Out-of-Domain Generalization
by: Wang, Siqi, et al.
Published: (2025)

Designing a Conditional Prior Distribution for Flow-Based Generative Models
by: Issachar, Noam, et al.
Published: (2025)

Data-Efficient Inference of Neural Fluid Fields via SciML Foundation Model
by: Liu, Yuqiu, et al.
Published: (2024)