Copertina

Improving the Training of Rectified Flows

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lee, Sangyun, Lin, Zinan, Fanti, Giulia
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Truncated Consistency Models
di: Lee, Sangyun, et al.
Pubblicazione: (2024)

Understanding, Accelerating, and Improving MeanFlow Training
di: Kim, Jin-Young, et al.
Pubblicazione: (2025)

DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding
di: Cho, Jungbin, et al.
Pubblicazione: (2024)

FSL-Rectifier: Rectify Outliers in Few-Shot Learning via Test-Time Augmentation
di: Bai, Yunwei, et al.
Pubblicazione: (2024)

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

Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance
di: Ahn, Donghoon, et al.
Pubblicazione: (2024)

REG: Rectified Gradient Guidance for Conditional Diffusion Models
di: Gao, Zhengqi, et al.
Pubblicazione: (2025)

BaNEL: Exploration Posteriors for Generative Modeling Using Only Negative Rewards
di: Lee, Sangyun, et al.
Pubblicazione: (2025)

Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification
di: Lin, Zinan, et al.
Pubblicazione: (2025)

SuperEdit: Rectifying and Facilitating Supervision for Instruction-Based Image Editing
di: Li, Ming, et al.
Pubblicazione: (2025)

UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures
di: Le, Triet M.
Pubblicazione: (2026)

NinA: Normalizing Flows in Action. Training VLA Models with Normalizing Flows
di: Tarasov, Denis, et al.
Pubblicazione: (2025)

VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide
di: Lee, Dohun, et al.
Pubblicazione: (2024)

CMT: Mid-Training for Efficient Learning of Consistency, Mean Flow, and Flow Map Models
di: Hu, Zheyuan, et al.
Pubblicazione: (2025)

Training-free Linear Image Inverses via Flows
di: Pokle, Ashwini, et al.
Pubblicazione: (2023)

Constant Acceleration Flow
di: Park, Dogyun, et al.
Pubblicazione: (2024)

Detection Limits and Statistical Separability of Tree Ring Watermarks in Rectified Flow-based Text-to-Image Generation Models
di: Umrajkar, Ved, et al.
Pubblicazione: (2025)

MixFlow: Mixed Source Distributions Improve Rectified Flows
di: Nayal, Nazir, et al.
Pubblicazione: (2026)

VeCLIP: Improving CLIP Training via Visual-enriched Captions
di: Lai, Zhengfeng, et al.
Pubblicazione: (2023)

Training-free Detection of AI-generated images via Cropping Robustness
di: Choi, Sungik, et al.
Pubblicazione: (2025)

Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models
di: Zou, Jade, et al.
Pubblicazione: (2026)

Changing the Training Data Distribution to Reduce Simplicity Bias Improves In-distribution Generalization
di: Nguyen, Dang, et al.
Pubblicazione: (2024)

DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization
di: Lee, Dongyeun, et al.
Pubblicazione: (2025)

Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning
di: Kim, Donghu, et al.
Pubblicazione: (2024)

From Baselines to Transport Geodesics: Axiomatic Attribution via Optimal Generative Flows
di: Zhang, Cenwei, et al.
Pubblicazione: (2026)

FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed
di: Zhang, Jiaqi, et al.
Pubblicazione: (2025)

Training-Free Restoration of Pruned Neural Networks
di: Lee, Keonho, et al.
Pubblicazione: (2025)

Improving Object Detection Performance through YOLOv8: A Comprehensive Training and Evaluation Study
di: Poureskandar, Rana, et al.
Pubblicazione: (2025)

DMin: Scalable Training Data Influence Estimation for Diffusion Models
di: Lin, Huawei, et al.
Pubblicazione: (2024)

Improved Sub-Visible Particle Classification in Flow Imaging Microscopy via Generative AI-Based Image Synthesis
di: Ozbulak, Utku, et al.
Pubblicazione: (2025)

Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models
di: Ahn, Donghoon, et al.
Pubblicazione: (2025)

Robust Self-Training with Closed-loop Label Correction for Learning from Noisy Labels
di: Lin, Zhanhui, et al.
Pubblicazione: (2026)

Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models
di: Lee, Jeongjae, et al.
Pubblicazione: (2026)

AROID: Improving Adversarial Robustness Through Online Instance-Wise Data Augmentation
di: Li, Lin, et al.
Pubblicazione: (2023)

Self-Supervised Multi-Frame Neural Scene Flow
di: Liu, Dongrui, et al.
Pubblicazione: (2024)

Thought Flow Nets: From Single Predictions to Trains of Model Thought
di: Schuff, Hendrik, et al.
Pubblicazione: (2021)

MobileCLIP2: Improving Multi-Modal Reinforced Training
di: Faghri, Fartash, et al.
Pubblicazione: (2025)

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

RAC: Rectified Flow Auto Coder
di: Fang, Sen, et al.
Pubblicazione: (2026)

Fine Structure-Aware Sampling: A New Sampling Training Scheme for Pixel-Aligned Implicit Models in Single-View Human Reconstruction
di: Chan, Kennard Yanting, et al.
Pubblicazione: (2024)